TL;DR
A photometric stereo problem of input images by a grouping-and-merging strategy that enables reconstruction and relighting of dark scenes and outperforms state-of-the-art approaches in decomposition, geometry, and relighting.
Robots operating in dark or poorly lit environments rely on onboard lights, which often produce uneven illumination that degrades downstream perception tasks. Prior approaches based on 2D image enhancement lack reliable supervision and fail to preserve multi-view geometric consistency. To address these limitations, we...
A surface photographed under even light presents nearly the same appearance from every angle; the same surface under uneven light does not. Exposure changes between views, illumination varies within a single image, and locally strong light sources leave one region bright and its neighbor in shadow. Multi-view reconstru...
This work introduces an exact analytical pixel-to-texel mapping that aligns diffusion trajectories across multiple viewpoints, and utilizes High-Resolution Latent Textures as a persistent canvas for gradually denoised textures, while camera views perform the denoising steps in latent pixel space.
SPVC is introduced, a structured and panoptic video fixing framework for cross-dataset driving scene rendering that first addresses video-level appearance and then refines scene layout with structured controls.
An event-guided image reconstruction method for nighttime dynamic visual perception that constructs a multi-channel event voxel representation by jointly encoding event count, event intensity, timestamp distribution, and blurred-frame intensity priors is proposed.
Standard 3D Gaussian Splatting (3DGS) learns geometry and appearance jointly from RGB supervision, making it difficult to isolate how luminance and chroma contribute to the learned representation. We study this by training models under different channel supervision, freezing their non-appearance parameters (position, s...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
