SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2202.05263 · CVPR · 2022

Block-NeRF: Scalable Large Scene Neural View Synthesis

Henrik Kretzschmar, Matthew Tancik, Xinchen Yan, Sabeek Pradhan, Vincent Casser, B. Mildenhall, P. Srinivasan, J. Barron

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 14 functions out of this paper's own repositories and ran 10 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
dvlab-research/LargeScaleNeRFPytorch pwc_unofficial 10 of 14
FunctionStatusWhere it lives
FourierGrid_compute_bbox_by_cam_frustrm_waymo Ran dvlab-research/LargeScaleNeRFPytorch/FourierGrid/bbox_compute.py
code served (permissive licence) · get_code("ab783a8f16a37718")
convert_to_ndc Ran dvlab-research/LargeScaleNeRFPytorch/FourierGrid/camera_utils.py
code served (permissive licence) · get_code("ce266e17c5088b07")
create_full_step_id Ran dvlab-research/LargeScaleNeRFPytorch/FourierGrid/dmpigo.py
code served (permissive licence) · get_code("eb2f4df4e13ab013")
filter_Block Ran dvlab-research/LargeScaleNeRFPytorch/eval_block_nerf.py
code served (permissive licence) · get_code("cf4cfe9b84749e46")
filter_cam_info_by_index Ran dvlab-research/LargeScaleNeRFPytorch/eval_block_nerf.py
code served (permissive licence) · get_code("756fbe4497eabee7")
get_rays Ran dvlab-research/LargeScaleNeRFPytorch/FourierGrid/FourierGrid_model.py
code served (permissive licence) · get_code("049307a781780caa")
get_rays_of_a_view Ran dvlab-research/LargeScaleNeRFPytorch/FourierGrid/FourierGrid_model.py
code served (permissive licence) · get_code("2703eb1cf816a1af")
intrinsic_matrix Ran dvlab-research/LargeScaleNeRFPytorch/FourierGrid/camera_utils.py
code served (permissive licence) · get_code("278d19a408119216")
ndc_rays Ran dvlab-research/LargeScaleNeRFPytorch/FourierGrid/FourierGrid_model.py
code served (permissive licence) · get_code("4366d225ac2fe16d")
split_rays Ran dvlab-research/LargeScaleNeRFPytorch/FourierGrid/camera_utils.py
code served (permissive licence) · get_code("c38d089d67862202")
FourierGrid_compute_bbox_by_cam_frustrm_mega Not yet run dvlab-research/LargeScaleNeRFPytorch/FourierGrid/bbox_compute.py
code served (permissive licence) · get_code("ba84c492683659b1")
batched_inference Not yet run dvlab-research/LargeScaleNeRFPytorch/eval_block_nerf.py
code served (permissive licence) · get_code("bec3e39fd4aacd1e")
compute_tensorf_feat Not yet run dvlab-research/LargeScaleNeRFPytorch/FourierGrid/FourierGrid_grid.py
code served (permissive licence) · get_code("67fd5c6c899ca0af")
compute_tensorf_val Not yet run dvlab-research/LargeScaleNeRFPytorch/FourierGrid/FourierGrid_grid.py
code served (permissive licence) · get_code("e6262a56833bb6d2")

Repositories linked to this paper

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

Abstract

Figure 1. Block-NeRF is a method that enables large-scale scene reconstruction by representing the environment using multiple compact NeRFs that each fit into memory. At inference time, Block-NeRF seamlessly combines renderings of the relevant NeRFs for the given area. In this example, we reconstruct the Alamo Square neighborhood in San Francisco using data collected over 3 months. Block-NeRF can update individual blocks of the environment without retraining on the entire scene, as demonstrated by the construction on the right. Video results can be found on the project website waymo.com/research/block-nerf.

For agents

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

get_harvested_code_for_paper("2202.05263")
get_code_for_paper("2202.05263")
have("2202.05263")

Connect an agent — have() is free.