Featured

HKU open-sources GenSfM: jointly reconstructing 3D objects and camera poses from four uncalibrated images

A University of Hong Kong team has open-sourced GenSfM, which uses a native 3D diffusion model to jointly denoise object shape and per-view camera poses within a single multimodal sequence, requiring only 2 to 4 uncalibrated images and no camera intrinsics or extrinsics. Evaluated on Toys4k and GSO, it improves novel-view PSNR by 3.2–4.5 dB over the multi-view baseline TRELLIS-M, reduces median Chamfer distance by about 64%–74%, and achieves pose Acc@5° above 96%.

Part of the event: HKU Open-Sources GenSfM: Joint Reconstruction of Objects and Poses from Four Views

This page provides a summary and source link only.