activity
20242026
collaborators

6 papers

cs.CV2026

InvSplat: Inverse Feed-Forward Scene Splatting

Polina Karpikova, Wenjing Bian, Haofei Xu +2

Inverse rendering aims to recover both 3D geometry and physically meaningful material properties from images, enabling applications such as relighting and novel view synthesis. Opt…

cs.CV2026

Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective

Weijie Wang, Qihang Cao, Sensen Gao +10

Reconstructing 3D representations from 2D inputs is a fundamental task in computer vision and graphics, serving as a cornerstone for understanding and interacting with the physical…

cs.CV2025

Scene Coordinate Reconstruction Priors

Wenjing Bian, Axel Barroso-Laguna, Tommaso Cavallari +2

Scene coordinate regression (SCR) models have proven to be powerful implicit scene representations for 3D vision, enabling visual relocalization and structure-from-motion. SCR mode…

cs.CV2025

Seeing in the Dark: Benchmarking Egocentric 3D Vision with the Oxford Day-and-Night Dataset

Zirui Wang, Wenjing Bian, Xinghui Li +4

We introduce Oxford Day-and-Night, a large-scale, egocentric dataset for novel view synthesis (NVS) and visual relocalisation under challenging lighting conditions. Existing datase…

cs.CV2024

CatFree3D: Category-agnostic 3D Object Detection with Diffusion

Wenjing Bian, Zirui Wang, Andrea Vedaldi

Image-based 3D object detection is widely employed in applications such as autonomous vehicles and robotics, yet current systems struggle with generalisation due to complex problem…

cs.CV2024

CrossScore: Towards Multi-View Image Evaluation and Scoring

Zirui Wang, Wenjing Bian, Victor Adrian Prisacariu

We introduce a novel cross-reference image quality assessment method that effectively fills the gap in the image assessment landscape, complementing the array of established evalua…