SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2308.02908 · 2023

Where and How: Mitigating Confusion in Neural Radiance Fields from Sparse Inputs

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 10 functions out of this paper's own repositories and ran 9 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
bbbbby-99/wah-nerf canonical 9 of 10
FunctionStatusWhere it lives
convert_to_ndc Ran bbbbby-99/wah-nerf/WaHNeRF/ray_utils.py
pointer only (licence: NONE) · get_code("2530cb2ea3170f45")
def_perturb Ran bbbbby-99/wah-nerf/WaHNeRF/model.py
pointer only (licence: NONE) · get_code("c6dc6cf8ed2b25d8")
def_perturb Ran bbbbby-99/wah-nerf/WaHNeRF/pose_utils.py
pointer only (licence: NONE) · get_code("9f029eb96e76e2ef")
generate_spiral_cam_to_world Ran bbbbby-99/wah-nerf/WaHNeRF/pose_utils.py
pointer only (licence: NONE) · get_code("131faedd2efa858c")
getMask Ran bbbbby-99/wah-nerf/WaHNeRF/model.py
pointer only (licence: NONE) · get_code("0c4861af050a8b92")
loss_dist Ran bbbbby-99/wah-nerf/WaHNeRF/model.py
pointer only (licence: NONE) · get_code("5fc4001620253191")
mse_to_psnr Ran bbbbby-99/wah-nerf/WaHNeRF/loss.py
pointer only (licence: NONE) · get_code("571b8d3310f49386")
namedtuple_map Ran bbbbby-99/wah-nerf/WaHNeRF/ray_utils.py
pointer only (licence: NONE) · get_code("f2267c6893ffb35f")
sorted_piecewise_constant_pdf Ran bbbbby-99/wah-nerf/WaHNeRF/ray_utils.py
pointer only (licence: NONE) · get_code("1938594a08c5dd74")
generate_spherical_cam_to_world Not yet run bbbbby-99/wah-nerf/WaHNeRF/pose_utils.py
pointer only (licence: NONE) · get_code("147422cf03df7064")

Repositories linked to this paper

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

Abstract

Neural Radiance Fields from Sparse input} (NeRF-S) have shown great potential in synthesizing novel views with a limited number of observed viewpoints. However, due to the inherent limitations of sparse inputs and the gap between non-adjacent views, rendering results often suffer from over-fitting and foggy surfaces, a phenomenon we refer to as "CONFUSION" during volume rendering. In this paper, we analyze the root cause of this confusion and attribute it to two fundamental questions: "WHERE" and "HOW". To this end, we present a novel learning framework, WaH-NeRF, which effectively mitigates confusion by tackling the following challenges: (i)"WHERE" to Sample? in NeRF-S -- we introduce a Deformable Sampling strategy and a Weight-based Mutual Information Loss to address sample-position confusion arising from the limited number of viewpoints; and (ii) "HOW" to Predict? in NeRF-S -- we propose a Semi-Supervised NeRF learning Paradigm based on pose perturbation and a Pixel-Patch Correspondence Loss to alleviate prediction confusion caused by the disparity between training and testing viewpoints. By integrating our proposed modules and loss functions, WaH-NeRF outperforms previous methods under the NeRF-S setting. Code is available https://github.com/bbbbby-99/WaH-NeRF.

For agents

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

get_harvested_code_for_paper("2308.02908")
get_code_for_paper("2308.02908")
have("2308.02908")

Connect an agent — have() is free.