Naiyan Wang, Zhaoxiang Zhang, Yuntao Chen, Jiawei He
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We explore long-term temporal visual correspondencebased optimization for 3D video object detection in this work. Visual correspondence refers to one-to-one mappings for pixels across multiple images. Correspondencebased optimization is the cornerstone for 3D scene reconstruction but is less studied in 3D video object detection, because moving objects violate multi-view geometry constraints and are treated as outliers during scene reconstruction. We address this issue by treating objects as first-class citizens during correspondence-based optimization. In this work, we propose BA-Det, an end-to-end optimizable object detector with object-centric temporal correspondence learning and featuremetric object bundle adjustment. Empirically, we verify the effectiveness and efficiency of BA-Det for multiple baseline 3D detectors under various setups. Our BA-Det achieves SOTA performance on the large-scale Waymo Open Dataset (WOD) with only marginal computation cost. Our code is available at https://github.com/jiaweihe1996/BA-Det.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2303.15416")
get_code_for_paper("2303.15416")
have("2303.15416")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2303.15416.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2303.15416)
Connect an agent — have() is free.