Reproduce “4D Reconstruction with Events & RGB” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Dulanga Weerakoon, Darshana Rathnayake, Van Minh Do, Hemanth Sabbella, Kaichen Zhou, Fangneng Zhan, Alok Prakash, Sanjay E. Sarma and 2 more
The authors extend MonST3R, a video-based 4D reconstruction system, with event data to estimate scene depth and motion. They convert brightness changes into five-bin event voxel grids and combine them with RGB inputs through an adapter, retaining the pretrained model’s main pipeline. On three depth datasets, fusion reports a 3.4% average Abs Rel reduction; events are simulated, and training differences limit attribution.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.