# DarkVGGT: Seeing Through Darkness Using Thermal Geometry without Daylight Tax

Source: [DarkVGGT: Seeing Through Darkness Using Thermal Geometry without Daylight Tax](<https://www.sota2.com/research/paper/6a2a40eed33dfb23e78391ad>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-07-04T05:01:04.041Z

Authors: Minseong Kweon, Wenyuan Zhao, Nuo Chen, Lulin Liu, Huiwen Han, Zihao Zhu, Srinivas Shakkottai, Chao Tian, Zhiwen Fan

Published: 2026-06-09T18:08:51.000Z

## Abstract

Recent feed-forward 3D reconstruction methods have demonstrated strong performance and flexibility in efficient end-to-end scene geometry estimation from image streams. However, their reliance on visible-light appearance makes them vulnerable in dark and low-visibility environments, where RGB cues are severely degraded and geometric evidence becomes ambiguous. To address this challenge, we propose DarkVGGT, an RGB-T feed-forward geometry framework that uses physics-aware thermal modeling for robust 3D estimation in low-light scenes. DarkVGGT introduces two complementary modules. First, physics-inspired thermal factorization extracts emissive-dominant, geometry-consistent thermal cues while isolating sparse reflective residuals that may introduce geometric ambiguity. Second, geometry-shared thermal routing isolates modality-invariant geometric structures from thermal-specific patterns, selectively injecting reliability-aware structural guidance into the RGB stream. Together, these components enable accurate thermal-informed geometry estimation under degraded RGB conditions while largely preserving performance in well-lit environments. Experiments on low-visibility RGB-T benchmarks demonstrate consistent improvements in both depth and camera pose estimation over existing feed-forward geometry baselines.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Camera Pose Estimation on ViViD++](<https://www.sota2.com/research/sota/camera-pose-estimation-on-vivid-plus-plus.md>): Camera pose estimation; ViViD++; RRA@30: 98.

- [Depth Estimation on ViViD++ (indoor\_aggresive\_dark, indoor\_unstable\_dark, outdoor\_robust\_night2)](<https://www.sota2.com/research/sota/depth-estimation-on-vivid-plus-plus-indoor_aggresive_dark-indoor_unstable_dark-outdoor_robust_night2.md>): Depth Estimation; ViViD++ indoor\_aggresive\_dark, indoor\_unstable\_dark, outdoor\_robust\_night2; AbsRel: 0.1274.

- [Depth Estimation on STheReO kaist\_evening, valley\_evening](<https://www.sota2.com/research/sota/depth-estimation-on-sthereo-kaist_evening-valley_evening.md>): Depth Estimation; STheReO kaist\_evening, valley\_evening; AbsRel: 0.16.

- [Depth Estimation on Dark3R (dark\_chapel, dark\_kitchen)](<https://www.sota2.com/research/sota/depth-estimation-on-dark3r-dark_chapel-dark_kitchen.md>): Depth Estimation; Dark3R (dark\_chapel, dark\_kitchen); Abs Rel: 0.1246.

- [Camera Pose Estimation on STheReO](<https://www.sota2.com/research/sota/camera-pose-estimation-on-sthereo.md>): Camera pose estimation; STheReO; RRA@30: 100.

- [Camera Pose Estimation on Dark3R](<https://www.sota2.com/research/sota/camera-pose-estimation-on-dark3r.md>): Camera pose estimation; Dark3R; RRA (30 deg): 100.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2606.11326>)

[PDF](<https://arxiv.org/pdf/2606.11326.pdf>)