SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2412.09043 · 2024

DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 15 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
envision-research/driverecon canonical 1 of 15
FunctionStatusWhere it lives
readImages Ran envision-research/driverecon/metrics.py
pointer only (licence: NONE) · get_code("cdd00787894554b5")
add_residual Not yet run envision-research/driverecon/dinov2/layers/block.py
pointer only (licence: NONE) · get_code("5d16d4d4fc573ac7")
compute_depth Not yet run envision-research/driverecon/utils/loss_utils.py
pointer only (licence: NONE) · get_code("da5e89413133330c")
coords_grid Not yet run envision-research/driverecon/scene/PointNet.py
pointer only (licence: NONE) · get_code("134980aa63271fbb")
drop_add_residual_stochastic_depth Not yet run envision-research/driverecon/dinov2/layers/block.py
pointer only (licence: NONE) · get_code("85f7ffc01945bb72")
get_branges_scales Not yet run envision-research/driverecon/dinov2/layers/block.py
pointer only (licence: NONE) · get_code("5be3610fa1fee19e")
get_directions Not yet run envision-research/driverecon/scene/background_model.py
pointer only (licence: NONE) · get_code("175e3da7503633f8")
get_ground_np Not yet run envision-research/driverecon/waymo_preprocess.py
pointer only (licence: NONE) · get_code("ce63f0de3afe4554")
get_rays Not yet run envision-research/driverecon/scene/background_model.py
pointer only (licence: NONE) · get_code("317bf63cf42925ff")
init_pool Not yet run envision-research/driverecon/waymo_preprocess.py
pointer only (licence: NONE) · get_code("fa28b3cfd6890d3b")
min_max Not yet run envision-research/driverecon/scene/background_model.py
pointer only (licence: NONE) · get_code("c9cb5e3906f5e9db")
normalize_depth Not yet run envision-research/driverecon/utils/loss_utils.py
pointer only (licence: NONE) · get_code("10f6c504485a371d")
pearson_similarity Not yet run envision-research/driverecon/utils/loss_utils.py
pointer only (licence: NONE) · get_code("6c6230c0c96f18aa")
track_parallel_progress Not yet run envision-research/driverecon/waymo_preprocess.py
pointer only (licence: NONE) · get_code("6d5f33814a53cca2")
warp_with_pose_depth_candidates Not yet run envision-research/driverecon/scene/PointNet.py
pointer only (licence: NONE) · get_code("d809e823c4e3678d")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Photorealistic 4D reconstruction of street scenes is essential for developing real-world simulators in autonomous driving. However, most existing methods perform this task offline and rely on time-consuming iterative processes, limiting their practical applications. To this end, we introduce the Large 4D Gaussian Reconstruction Model (DrivingRecon), a generalizable driving scene reconstruction model, which directly predicts 4D Gaussian from surround view videos. To better integrate the surround-view images, the Prune and Dilate Block (PD-Block) is proposed to eliminate overlapping Gaussian points between adjacent views and remove redundant background points. To enhance cross-temporal information, dynamic and static decoupling is tailored to better learn geometry and motion features. Experimental results demonstrate that DrivingRecon significantly improves scene reconstruction quality and novel view synthesis compared to existing methods. Furthermore, we explore applications of DrivingRecon in model pre-training, vehicle adaptation, and scene editing. Our code is available at https://github.com/EnVision-Research/DriveRecon.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2412.09043")
get_code_for_paper("2412.09043")
have("2412.09043")

Connect an agent — have() is free.