Matthieu Cord, Alexandre Boulch, Mickaël Chen, Loïck Chambon, Eloi Zablocki
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.
Understanding the 3D geometry and semantics of driving scenes is critical for safe autonomous driving. Recent advances in 3D occupancy prediction have improved scene representation but often suffer from visual inconsistencies, leading to floating artifacts and poor surface localization. Existing voxel-wise losses (e.g., cross-entropy) fail to enforce visible geometric coherence. In this paper, we propose GaussRender, a module that improves 3D occupancy learning by enforcing projective consistency. Our key idea is to project both predicted and groundtruth 3D occupancy into 2D camera views, where we apply supervision. Our method penalizes 3D configurations that produce inconsistent 2D projections, thereby enforcing a more coherent 3D structure. To achieve this efficiently, we leverage differentiable rendering with Gaussian splatting. GaussRender seamlessly integrates with existing architectures while maintaining efficiency and requiring no inference-time modifications. Extensive evaluations on multiple benchmarks (SurroundOcc-nuScenes, Occ3D-nuScenes, SSCBench-KITTI360) demonstrate that Gauss-Render significantly improves geometric fidelity across various 3D occupancy models (TPVFormer, SurroundOcc, Symphonies), achieving state-of-the-art results, particularly on surface-sensitive metrics such as RayIoU. The code is open-sourced at https://github.com/valeoai/ GaussRender.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2502.05040")
get_code_for_paper("2502.05040")
have("2502.05040")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2502.05040.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2502.05040)
Connect an agent — have() is free.