Author name cluster

Fei Deng

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.

8 papers

2 author rows

IROS Conference 2025 Conference Paper

RA-NeRF: Robust Neural Radiance Field Reconstruction with Accurate Camera Pose Estimation under Complex Trajectories

Qingsong Yan
Qiang Wang 0022
Kaiyong Zhao
Jie Chen 0026
Bo Li 0001
Xiaowen Chu 0001
Fei Deng

Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have emerged as powerful tools for 3D reconstruction and SLAM tasks. However, their performance depends heavily on accurate camera pose priors. Existing approaches attempt to address this issue by introducing external constraints but fall short of achieving satisfactory accuracy, particularly when camera trajectories are complex. In this paper, we propose a novel method, RA-NeRF, capable of predicting highly accurate camera poses even with complex camera trajectories. Following the incremental pipeline, RA-NeRF reconstructs the scene using NeRF with photometric consistency and incorporates flow-driven pose regulation to enhance robustness during initialization and localization. Additionally, RA-NeRF employs an implicit pose filter to capture the camera movement pattern and eliminate the noise for pose estimation. To validate our method, we conduct extensive experiments on the Tanks&Temple dataset for standard evaluation, as well as the NeRFBuster dataset, which presents challenging camera pose trajectories. On both datasets, RA-NeRF achieves state-of-the-art results in both camera pose estimation and visual quality, demonstrating its effectiveness and robustness in scene reconstruction under complex pose trajectories.

Details

AAAI Conference 2024 Conference Paper

CF-NeRF: Camera Parameter Free Neural Radiance Fields with Incremental Learning

Qingsong Yan
Qiang Wang
Kaiyong Zhao
Jie Chen
Bo Li
Xiaowen Chu
Fei Deng

Neural Radiance Fields have demonstrated impressive performance in novel view synthesis. However, NeRF and most of its variants still rely on traditional complex pipelines to provide extrinsic and intrinsic camera parameters, such as COLMAP. Recent works, like NeRFmm, BARF, and L2G-NeRF, directly treat camera parameters as learnable and estimate them through differential volume rendering. However, these methods work for forward-looking scenes with slight motions and fail to tackle the rotation scenario in practice. To overcome this limitation, we propose a novel camera parameter free neural radiance field (CF-NeRF), which incrementally reconstructs 3D representations and recovers the camera parameters inspired by incremental structure from motion. Given a sequence of images, CF-NeRF estimates camera parameters of images one by one and reconstructs the scene through initialization, implicit localization, and implicit optimization. To evaluate our method, we use a challenging real-world dataset, NeRFBuster, which provides 12 scenes under complex trajectories. Results demonstrate that CF-NeRF is robust to rotation and achieves state-of-the-art results without providing prior information and constraints.

PDF Details DOI

EAAI Journal 2024 Journal Article

Multi-level attention network: Mixed time–frequency channel attention and multi-scale self-attentive standard deviation pooling for speaker recognition

Lihong Deng
Fei Deng
Kepeng Zhou
Peifan Jiang
Gexiang Zhang
Qiang Yang

In this paper, we propose a more efficient lightweight speaker recognition network, the multi-level attention network (MANet). MANet aims to generate more robust and discriminative speaker features by emphasizing features at different levels in the speaker recognition network through multi-level attention. The multi-level attention contains mixed time–frequency channel (MTFC) attention and multi-scale self-attentive standard deviation pooling (MSSDP). MTFC attention combines channel, time, and frequency information to capture global features and model long-term contexts. MSSDP can capture changes in frame-level features and aggregate frame-level features with different scales, generating a long-term, robust, and discriminative utterance-level feature. Therefore, MANet emphasizes the features of different levels. We performed extensive experiments on two popular datasets, Voxceleb and CN-Celeb. The proposed method is compared with the current state-of-the-art speaker recognition methods. It achieved EER/minDCF of 1. 82%/0. 1965, 1. 94%/0. 2059, 3. 69%/0. 3626, and 11. 98%/0. 4814 on the test sets Voxceleb1-O, Voxceleb1-E, Voxceleb1-H, and CN-Celeb, respectively. It is a more effective lightweight speaker recognition network, superior to most large speaker recognition networks and all lightweight speaker recognition networks tested, with an improved performance of 64% compared to the baseline system ThinResNet-34. Compared to the lightest EfficientTDNN-Small, it has only 0. 6 million more parameters but 63% better performance. The performance of MANet is only 4% different compared to the state-of-the-art large model LE-Conformer. In the ablation experiments, our proposed attention method and aggregation model achieved the best experimental performance in Voxceleb1-O with EER/minDCF of 2. 46%/0. 2708, 2. 39%/0. 2417, respectively, which indicates that our proposed methods are a significant improvement over previous methods.

Details DOI

NeurIPS Conference 2024 Conference Paper

Slot State Space Models

Jindong Jiang
Fei Deng
Gautam Singh
Minseung Lee
Sungjin Ahn

Recent State Space Models (SSMs) such as S4, S5, and Mamba have shown remarkable computational benefits in long-range temporal dependency modeling. However, in many sequence modeling problems, the underlying process is inherently modular and it is of interest to have inductive biases that mimic this modular structure. In this paper, we introduce SlotSSMs, a novel framework for incorporating independent mechanisms into SSMs to preserve or encourage separation of information. Unlike conventional SSMs that maintain a monolithic state vector, SlotSSMs maintains the state as a collection of multiple vectors called slots. Crucially, the state transitions are performed independently per slot with sparse interactions across slots implemented via the bottleneck of self-attention. In experiments, we evaluate our model in object-centric learning, 3D visual reasoning, and long-context video understanding tasks, which involve modeling multiple objects and their long-range temporal dependencies. We find that our proposed design offers substantial performance gains over existing sequence modeling methods. Project page is available at \url{https: //slotssms. github. io/}

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Facing Off World Model Backbones: RNNs, Transformers, and S4

Fei Deng
Junyeong Park
Sungjin Ahn

World models are a fundamental component in model-based reinforcement learning (MBRL). To perform temporally extended and consistent simulations of the future in partially observable environments, world models need to possess long-term memory. However, state-of-the-art MBRL agents, such as Dreamer, predominantly employ recurrent neural networks (RNNs) as their world model backbone, which have limited memory capacity. In this paper, we seek to explore alternative world model backbones for improving long-term memory. In particular, we investigate the effectiveness of Transformers and Structured State Space Sequence (S4) models, motivated by their remarkable ability to capture long-range dependencies in low-dimensional sequences and their complementary strengths. We propose S4WM, the first world model compatible with parallelizable SSMs including S4 and its variants. By incorporating latent variable modeling, S4WM can efficiently generate high-dimensional image sequences through latent imagination. Furthermore, we extensively compare RNN-, Transformer-, and S4-based world models across four sets of environments, which we have tailored to assess crucial memory capabilities of world models, including long-term imagination, context-dependent recall, reward prediction, and memory-based reasoning. Our findings demonstrate that S4WM outperforms Transformer-based world models in terms of long-term memory, while exhibiting greater efficiency during training and imagination. These results pave the way for the development of stronger MBRL agents.

PDF Details

NeurIPS Conference 2023 Conference Paper

Object-Centric Slot Diffusion

Jindong Jiang
Fei Deng
Gautam Singh
Sungjin Ahn

The recent success of transformer-based image generative models in object-centric learning highlights the importance of powerful image generators for handling complex scenes. However, despite the high expressiveness of diffusion models in image generation, their integration into object-centric learning remains largely unexplored in this domain. In this paper, we explore the feasibility and potential of integrating diffusion models into object-centric learning and investigate the pros and cons of this approach. We introduce Latent Slot Diffusion (LSD), a novel model that serves dual purposes: it is the first object-centric learning model to replace conventional slot decoders with a latent diffusion model conditioned on object slots, and it is also the first unsupervised compositional conditional diffusion model that operates without the need for supervised annotations like text. Through experiments on various object-centric tasks, including the first application of the FFHQ dataset in this field, we demonstrate that LSD significantly outperforms state-of-the-art transformer-based decoders, particularly in more complex scenes, and exhibits superior unsupervised compositional generation quality. In addition, we conduct a preliminary investigation into the integration of pre-trained diffusion models in LSD and demonstrate its effectiveness in real-world image segmentation and generation. Project page is available at https: //latentslotdiffusion. github. io

PDF Details

AAAI Conference 2023 Conference Paper

Rethinking Disparity: A Depth Range Free Multi-View Stereo Based on Disparity

Qingsong Yan
Qiang Wang
Kaiyong Zhao
Bo Li
Xiaowen Chu
Fei Deng

Existing learning-based multi-view stereo (MVS) methods rely on the depth range to build the 3D cost volume and may fail when the range is too large or unreliable. To address this problem, we propose a disparity-based MVS method based on the epipolar disparity flow (E-flow), called DispMVS, which infers the depth information from the pixel movement between two views. The core of DispMVS is to construct a 2D cost volume on the image plane along the epipolar line between each pair (between the reference image and several source images) for pixel matching and fuse uncountable depths triangulated from each pair by multi-view geometry to ensure multi-view consistency. To be robust, DispMVS starts from a randomly initialized depth map and iteratively refines the depth map with the help of the coarse-to-fine strategy. Experiments on DTUMVS and Tanks\&Temple datasets show that DispMVS is not sensitive to the depth range and achieves state-of-the-art results with lower GPU memory.

PDF Details DOI

JMLR Journal 2021 Journal Article

ROOTS: Object-Centric Representation and Rendering of 3D Scenes

Chang Chen
Fei Deng
Sungjin Ahn

A crucial ability of human intelligence is to build up models of individual 3D objects from partial scene observations. Recent works either achieve object-centric generation but without the ability to infer the representation, or achieve 3D scene representation learning but without object-centric compositionality. Therefore, learning to both represent and render 3D scenes with object-centric compositionality remains elusive. In this paper, we propose a probabilistic generative model for learning to build modular and compositional 3D object models from partial observations of a multi-object scene. The proposed model can (i) infer the 3D object representations by learning to search and group object areas, and also (ii) render from an arbitrary viewpoint not only individual objects but also the full scene by compositing the objects. The entire learning process is unsupervised and end-to-end. In experiments, in addition to generation quality, we also demonstrate that the learned representation permits object-wise manipulation and novel scene generation, and generalizes to various settings. Results can be found on our project website: https://sites.google.com/view/roots3d [abs] [ pdf ][ bib ] &copy JMLR 2021. ( edit, beta )

PDF Details