5 papers
Learning 3D Reconstruction with Priors in Test Time
Lei Zhou, Haoyu Wu, Akshat Dave +1
We introduce a test-time framework for multiview Transformers (MVTs) that incorporates priors (e.g., camera poses, intrinsics, and depth) to improve 3D tasks without retraining or…
Poppy: Polarization-based Plug-and-Play Guidance for Enhancing Monocular Normal Estimation
Irene Kim, Sai Tanmay Reddy Chakkera, Alexandros Graikos +2
Monocular surface normal estimators trained on large-scale RGB-normal data often perform poorly in the edge cases of reflective, textureless, and dark surfaces. Polarization encode…
Embedding Physical Reasoning into Diffusion-Based Shadow Generation Under the Sun and Sky
Shilin Hu, Jingyi Xu, Akshat Dave +2
Generating realistic cast shadows for inserted foreground objects requires reasoning about scene geometry and illumination. However, most learning-based approaches treat shadow gen…
SuperEx: Enhancing Indoor Mapping and Exploration using Non-Line-of-Sight Perception
Kush Garg, Akshat Dave
Efficient exploration and mapping in unknown indoor environments is a fundamental challenge, with high stakes in time-critical settings. In current systems, robot perception remain…
TranSplat: Instant Object Relighting in Gaussian Splatting via Spherical Harmonic Radiance Transfer
Boyang Tony Yu, Yanlin Jin, Yun He +3
We present TranSplat, a method for instant, accurate object relighting within the Gaussian Splatting (GS) framework. Rather than relying on costly inverse rendering routines, we pr…