Author name cluster

William Smith

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.

3 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

TAPVid-360: Tracking Any Point in 360 from Narrow Field of View Video

Finlay Hudson
James Gardner
William Smith

Humans excel at constructing panoramic mental models of their surroundings, maintaining object permanence and inferring scene structure beyond visible regions. In contrast, current artificial vision systems struggle with persistent, panoramic understanding, often processing scenes egocentrically on a frame-by-frame basis. This limitation is pronounced in the Track Any Point (TAP) task, where existing methods fail to track 2D points outside the field of view. To address this, we introduce TAP-Vid 360, a novel task that requires predicting the 3D direction to queried scene points across a video sequence, even when far outside the narrow field of view of the observed video. This task fosters learning allocentric scene representations without needing dynamic 4D ground truth scene models for training. Instead, we exploit 360 videos as a source of supervision, resampling them into narrow field-of-view perspectives while computing ground truth directions by tracking points across the full panorama using a 2D pipeline. We introduce a new dataset and benchmark, TAP360-10k comprising 10k perspective videos with ground truth directional point tracking. Our baseline adapts CoTracker v3 to predict per-point rotations for direction updates, outperforming existing TAP and TAP-Vid 3D methods.

PDF Details

NeurIPS Conference 2022 Conference Paper

Rotation-Equivariant Conditional Spherical Neural Fields for Learning a Natural Illumination Prior

James Gardner
Bernhard Egger
William Smith

Inverse rendering is an ill-posed problem. Previous work has sought to resolve this by focussing on priors for object or scene shape or appearance. In this work, we instead focus on a prior for natural illuminations. Current methods rely on spherical harmonic lighting or other generic representations and, at best, a simplistic prior on the parameters. We propose a conditional neural field representation based on a variational auto-decoder with a SIREN network and, extending Vector Neurons, build equivariance directly into the network. Using this, we develop a rotation-equivariant, high dynamic range (HDR) neural illumination model that is compact and able to express complex, high-frequency features of natural environment maps. Training our model on a curated dataset of 1. 6K HDR environment maps of natural scenes, we compare it against traditional representations, demonstrate its applicability for an inverse rendering task and show environment map completion from partial observations.

PDF Details

IROS Conference 2011 Conference Paper

Fast computation of wheel-soil interactions for safe and efficient operation of mobile robots

Zhenzhong Jia
William Smith
Huei Peng

Hazardous terrains pose a crucial challenge to the operation of mobile robots, especially for military applications such as surveillance, casualty extraction, etc. To enable their safe and efficient operations, it is necessary to detect the terrain type and to modify operation and control strategies in real-time. Fast wheel-terrain interaction models suitable for real-time applications are thus important. In this paper, closed-form analytical expressions of the integrated stress equations were derived by quadratic approximation of the stresses along the wheel-soil interface. Meanwhile, the bulldozing resistance and the influence of grousers are also modeled for more accurate prediction of the vehicle motion. A non-iterative method was proposed to estimate the wheel-soil contact geometry, i. e. , the entry angle, according to the wheel load, by approximating the vertical pressure distribution with a sinusoidal function or linear function depending on the sinkage exponent of the soil. Computation efficiency is improved by avoiding traditional recursive solution of the model under binary search. Online prediction and real-time control could be possible by using the developed closed-from wheel-soil interaction model and the entry angle estimator.

Details