Author name cluster

Xueting Li

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

12 papers

2 author rows

ICLR Conference 2025 Conference Paper

Layout-your-3D: Controllable and Precise 3D Generation with 2D Blueprint

Junwei Zhou 0003
Xueting Li
Lu Qi 0001
Ming-Hsuan Yang 0001

We present Layout-Your-3D, a framework that allows controllable and compositional 3D generation from text prompts. Existing text-to-3D methods often struggle to generate assets with plausible object interactions or require tedious optimization processes. To address these challenges, our approach leverages 2D layouts as a blueprint to facilitate precise and plausible control over 3D generation. Starting with a 2D layout provided by a user or generated from a text description, we first create a coarse 3D scene using a carefully designed initialization process based on efficient reconstruction models. To enforce coherent global 3D layouts and enhance the quality of instance appearances, we propose a collision-aware layout optimization process followed by instance-wise refinement. Experimental results demonstrate that Layout-Your-3D yields more reasonable and visually appealing compositional 3D assets while significantly reducing the time required for each prompt. Additionally, Layout-Your-3D can be easily applicable to downstream tasks, such as 3D editing and object insertion.

Details

ICLR Conference 2025 Conference Paper

No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images

Botao Ye
Sifei Liu
Haofei Xu
Xueting Li
Marc Pollefeys
Ming-Hsuan Yang 0001
Songyou Peng

We introduce NoPoSplat, a feed-forward model capable of reconstructing 3D scenes parameterized by 3D Gaussians from unposed sparse multi-view images. Our model, trained exclusively with photometric loss, achieves real-time 3D Gaussian reconstruction during inference. To eliminate the need for accurate pose input during reconstruction, we anchor one input view's local camera coordinates as the canonical space and train the network to predict Gaussian primitives for all views within this space. This approach obviates the need to transform Gaussian primitives from local coordinates into a global coordinate system, thus avoiding errors associated with per-frame Gaussians and pose estimation. To resolve scale ambiguity, we design and compare various intrinsic embedding methods, ultimately opting to convert camera intrinsics into a token embedding and concatenate it with image tokens as input to the model, enabling accurate scene scale prediction. We utilize the reconstructed 3D Gaussians for novel view synthesis and pose estimation tasks and propose a two-stage coarse-to-fine pipeline for accurate pose estimation. Experimental results demonstrate that our pose-free approach can achieve superior novel view synthesis quality compared to pose-required methods, particularly in scenarios with limited input image overlap. For pose estimation, our method, trained without ground truth depth or explicit matching loss, significantly outperforms the state-of-the-art methods with substantial improvements. This work makes significant advances in pose-free generalizable 3D reconstruction and demonstrates its applicability to real-world scenarios. Code and trained models are available at https://noposplat.github.io/.

Details

ICLR Conference 2024 Conference Paper

3D Reconstruction with Generalizable Neural Fields using Scene Priors

Yang Fu
Shalini De Mello
Xueting Li
Amey Kulkarni
Jan Kautz
Xiaolong Wang 0004
Sifei Liu

High-fidelity 3D scene reconstruction has been substantially advanced by recent progress in neural fields. However, most existing methods train a separate network from scratch for each individual scene. This is not scalable, inefficient, and unable to yield good results given limited views. While learning-based multi-view stereo methods alleviate this issue to some extent, their multi-view setting makes it less flexible to scale up and to broad applications. Instead, we introduce training generalizable Neural Fields incorporating scene Priors (NFPs). The NFP network maps any single-view RGB-D image into signed distance and radiance values. A complete scene can be reconstructed by merging individual frames in the volumetric space WITHOUT a fusion module, which provides better flexibility. The scene priors can be trained on large-scale datasets, allowing for fast adaptation to the reconstruction of a new scene with fewer views. NFP not only demonstrates SOTA scene reconstruction performance and efficiency, but it also supports single-image novel-view synthesis, which is under-explored in neural fields. More qualitative results are available at: https://oasisyang.github.io/neural-prior.

Details

ICLR Conference 2024 Conference Paper

TUVF: Learning Generalizable Texture UV Radiance Fields

An-Chieh Cheng
Xueting Li
Sifei Liu
Xiaolong Wang 0004

Textures are a vital aspect of creating visually appealing and realistic 3D models. In this paper, we study the problem of generating high-fidelity texture given shapes of 3D assets, which has been relatively less explored compared with generic 3D shape modeling. Our goal is to facilitate a controllable texture generation process, such that one texture code can correspond to a particular appearance style independent of any input shapes from a category. We introduce Texture UV Radiance Fields (TUVF) that generate textures in a learnable UV sphere space rather than directly on the 3D shape. This allows the texture to be disentangled from the underlying shape and transferable to other shapes that share the same UV space, i.e., from the same category. We integrate the UV sphere space with the radiance field, which provides a more efficient and accurate representation of textures than traditional texture maps. We perform our experiments on synthetic and real-world object datasets where we achieve not only realistic synthesis but also substantial improvements over state-of-the-arts on texture controlling and editing.

Details

NeurIPS Conference 2023 Conference Paper

Generalizable One-shot 3D Neural Head Avatar

Xueting Li
Shalini De Mello
Sifei Liu
Koki Nagano
Umar Iqbal
Jan Kautz

We present a method that reconstructs and animates a 3D head avatar from a single-view portrait image. Existing methods either involve time-consuming optimization for a specific person with multiple images, or they struggle to synthesize intricate appearance details beyond the facial region. To address these limitations, we propose a framework that not only generalizes to unseen identities based on a single-view image without requiring person-specific optimization, but also captures characteristic details within and beyond the face area (e. g. hairstyle, accessories, etc. ). At the core of our method are three branches that produce three tri-planes representing the coarse 3D geometry, detailed appearance of a source image, as well as the expression of a target image. By applying volumetric rendering to the combination of the three tri-planes followed by a super-resolution module, our method yields a high fidelity image of the desired identity, expression and pose. Once trained, our model enables efficient 3D head avatar reconstruction and animation via a single forward pass through a network. Experiments show that the proposed approach generalizes well to unseen validation datasets, surpassing SOTA baseline methods by a large margin on head avatar reconstruction and animation.

PDF Details

ICLR Conference 2022 Conference Paper

Learning Continuous Environment Fields via Implicit Functions

Xueting Li
Shalini De Mello
Xiaolong Wang 0004
Ming-Hsuan Yang 0001
Jan Kautz
Sifei Liu

We propose a novel scene representation that encodes reaching distance -- the distance between any position in the scene to a goal along a feasible trajectory. We demonstrate that this environment field representation can directly guide the dynamic behaviors of agents in 2D mazes or 3D indoor scenes. Our environment field is a continuous representation and learned via a neural implicit function using discretely sampled training data. We showcase its application for agent navigation in 2D mazes, and human trajectory prediction in 3D indoor environments. To produce physically plausible and natural trajectories for humans, we additionally learn a generative model that predicts regions where humans commonly appear, and enforce the environment field to be defined within such regions. Extensive experiments demonstrate that the proposed method can generate both feasible and plausible trajectories efficiently and accurately.

Details

NeurIPS Conference 2021 Conference Paper

Learning 3D Dense Correspondence via Canonical Point Autoencoder

An-Chieh Cheng
Xueting Li
Min Sun
Ming-Hsuan Yang
Sifei Liu

We propose a canonical point autoencoder (CPAE) that predicts dense correspondences between 3D shapes of the same category. The autoencoder performs two key functions: (a) encoding an arbitrarily ordered point cloud to a canonical primitive, e. g. , a sphere, and (b) decoding the primitive back to the original input instance shape. As being placed in the bottleneck, this primitive plays a key role to map all the unordered point clouds on the canonical surface, and to be reconstructed in an ordered fashion. Once trained, points from different shape instances that are mapped to the same locations on the primitive surface are determined to be a pair of correspondence. Our method does not require any form of annotation or self-supervised part segmentation network and can handle unaligned input point clouds within a certain rotation range. Experimental results on 3D semantic keypoint transfer and part segmentation transfer show that our model performs favorably against state-of-the-art correspondence learning methods.

PDF Details

YNIMG Journal 2021 Journal Article

The effect of eye gaze direction on emotional mimicry: A multimodal study with electromyography and electroencephalography

Beibei Kuang
Xueting Li
Xintong Li
Mingxiao Lin
Shanrou Liu
Ping Hu

Emotional mimicry plays an important role in social interaction and is influenced by social context, especially eye gaze direction. However, the neural mechanism underlying the effect of eye gaze direction on emotional mimicry is unclear. Here, we explored how eye gaze direction influenced emotional mimicry with a combination of electromyography (EMG) and electroencephalography (EEG) techniques, which may provide a more comprehensive measure. To do this, we recorded facial EMG and scalp EEG signals simultaneously while participants observed emotional faces (happy vs. angry) with direct or averted gaze. Then, we split the EEG trials into two mimicry intensity categories (high mimicry intensity, HMI vs. low mimicry intensity, LMI) according to EMG activity. The ERP difference between HMI and LMI EEG trials revealed four ERP components (P50, P150, N200 and P300), and the effect of eye gaze direction on emotional mimicry was prominent on P300 at P7 and P8. Moreover, we also observed differences in the effect of eye gaze direction on mimicry of happy faces and angry faces, which were found on P300 at P7, as well as P150 at P7 and N200 at P7 and Pz. In short, the present study isolated the neural signals of emotional mimicry with a new multimodal method, and provided empirical neural evidence that eye gaze direction affected emotional mimicry.

Details DOI

NeurIPS Conference 2020 Conference Paper

Online Adaptation for Consistent Mesh Reconstruction in the Wild

Xueting Li
Sifei Liu
Shalini De Mello
Kihwan Kim
Xiaolong Wang
Ming-Hsuan Yang
Jan Kautz

This paper presents an algorithm to reconstruct temporally consistent 3D meshes of deformable object instances from videos in the wild. Without requiring annotations of 3D mesh, 2D keypoints, or camera pose for each video frame, we pose video-based reconstruction as a self-supervised online adaptation problem applied to any incoming test video. We first learn a category-specific 3D reconstruction model from a collection of single-view images of the same category that jointly predicts the shape, texture, and camera pose of an image. Then, at inference time, we adapt the model to a test video over time using self-supervised regularization terms that exploit temporal consistency of an object instance to enforce that all reconstructed meshes share a common texture map, a base shape, as well as parts. We demonstrate that our algorithm recovers temporally consistent and reliable 3D structures from videos of non-rigid objects including those of animals captured in the wild -- an extremely challenging task rarely addressed before.

PDF Details

NeurIPS Conference 2019 Conference Paper

Joint-task Self-supervised Learning for Temporal Correspondence

Xueting Li
Sifei Liu
Shalini De Mello
Xiaolong Wang
Jan Kautz
Ming-Hsuan Yang

This paper proposes to learn reliable dense correspondence from videos in a self-supervised manner. Our learning process integrates two highly related tasks: tracking large image regions and establishing fine-grained pixel-level associations between consecutive video frames. We exploit the synergy between both tasks through a shared inter-frame affinity matrix, which simultaneously models transitions between video frames at both the region- and pixel-levels. While region-level localization helps reduce ambiguities in fine-grained matching by narrowing down search regions; fine-grained matching provides bottom-up features to facilitate region-level localization. Our method outperforms the state-of-the-art self-supervised methods on a variety of visual correspondence tasks, including video-object and part-segmentation propagation, keypoint tracking, and object tracking. Our self-supervised method even surpasses the fully-supervised affinity feature representation obtained from a ResNet-18 pre-trained on the ImageNet.

PDF Details

YNIMG Journal 2016 Journal Article

Encodings of implied motion for animate and inanimate object categories in the two visual pathways

Zhengang Lu
Xueting Li
Ming Meng

Previous research has proposed two separate pathways for visual processing: the dorsal pathway for “where” information vs. the ventral pathway for “what” information. Interestingly, the middle temporal cortex (MT) in the dorsal pathway is involved in representing implied motion from still pictures, suggesting an interaction between motion and object related processing. However, the relationship between how the brain encodes implied motion and how the brain encodes object/scene categories is unclear. To address this question, fMRI was used to measure activity along the two pathways corresponding to different animate and inanimate categories of still pictures with different levels of implied motion speed. In the visual areas of both pathways, activity induced by pictures of humans and animals was hardly modulated by the implied motion speed. By contrast, activity in these areas correlated with the implied motion speed for pictures of inanimate objects and scenes. The interaction between implied motion speed and stimuli category was significant, suggesting different encoding mechanisms of implied motion for animate-inanimate distinction. Further multivariate pattern analysis of activity in the dorsal pathway revealed significant effects of stimulus category that are comparable to the ventral pathway. Moreover, still pictures of inanimate objects/scenes with higher implied motion speed evoked activation patterns that were difficult to differentiate from those evoked by pictures of humans and animals, indicating a functional role of implied motion in the representation of object categories. These results provide novel evidence to support integrated encoding of motion and object categories, suggesting a rethink of the relationship between the two visual pathways.

Details DOI

YNIMG Journal 2015 Journal Article

The artist emerges: Visual art learning alters neural structure and function

Alexander Schlegel
Prescott Alexander
Sergey V. Fogelson
Xueting Li
Zhengang Lu
Peter J. Kohler
Enrico Riley
Peter U. Tse

How does the brain mediate visual artistic creativity? Here we studied behavioral and neural changes in drawing and painting students compared to students who did not study art. We investigated three aspects of cognition vital to many visual artists: creative cognition, perception, and perception-to-action. We found that the art students became more creative via the reorganization of prefrontal white matter but did not find any significant changes in perceptual ability or related neural activity in the art students relative to the control group. Moreover, the art students improved in their ability to sketch human figures from observation, and multivariate patterns of cortical and cerebellar activity evoked by this drawing task became increasingly separable between art and non-art students. Our findings suggest that the emergence of visual artistic skills is supported by plasticity in neural pathways that enable creative cognition and mediate perceptuomotor integration.

Details DOI