Dark3R: Learning Structure from Motion in the Dark

Dimensions overall score 7.0

• Dark3R enables robust 3D reconstruction from extremely low-light images by distilling knowledge from large-scale 3D foundation models, opening up applications in surveillance and autonomous navigation. Our key insight is to adapt large-scale 3D foundation models to extreme low-light conditions through a teacher--student distillation process, enabling robust feature matching and camera pose estimation in low light.problem 35%
  Evidencepartial

  Dark3R enables robust 3D reconstruction from extremely low-light images by distilling knowledge from large-scale 3D foundation models, opening up applications in surveillance and autonomous navigation. Our key insight is to adapt large-scale 3D foundation models to extreme low-light conditions through a teacher--student distillation process, enabling robust feature matching and camera pose estimation in low light.

  Implicationpartial

  Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.

  Verificationpartial

  partial

• We introduce Dark3R, a framework for structure from motion in the dark that operates directly on raw images with signal-to-noise ratios (SNRs) below $-4$ dB -- a regime where conventional feature- and learning-based methods break down. Our key insight is to adapt large-scale 3D foundation models to extreme low-light conditions through a teacher--student distillation process, enabling robust feature matching and camera pose estimation in low light.method 35%
  Evidencepartial

  We introduce Dark3R, a framework for structure from motion in the dark that operates directly on raw images with signal-to-noise ratios (SNRs) below $-4$ dB -- a regime where conventional feature- and learning-based methods break down. Our key insight is to adapt large-scale 3D foundation models to extreme low-light conditions through a teacher--student distillation process, enabling robust feature matching and camera pose estimation in low light.

  Implicationpartial

  Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.

  Verificationpartial

  partial

• ScienceToStartup currently rates this 7.0/10 on the public viability pass. To train and evaluate our approach, we introduce a new, exposure-bracketed dataset that includes $\sim$42,000 multi-view raw images with ground-truth 3D annotations, and we demonstrate that Dark3R achieves state-of-the-art structure from motion in the low-SNR regime.result 35%
  Evidencepartial

  ScienceToStartup currently rates this 7.0/10 on the public viability pass. To train and evaluate our approach, we introduce a new, exposure-bracketed dataset that includes $\sim$42,000 multi-view raw images with ground-truth 3D annotations, and we demonstrate that Dark3R achieves state-of-the-art structure from motion in the low-SNR regime.

  Implicationpartial

  Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.

  Verificationpartial

  partial

• 3D Vision moved forward this cycle; last verified April 2026. Public score 7.0/10.why now 35%
  Evidencepartial

  3D Vision moved forward this cycle; last verified April 2026. Public score 7.0/10.

  Implicationpartial

  Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.

  Verificationpartial

  partial

Competitive landscape

Dark3R enables robust 3D reconstruction from extremely low-light images by distilling knowledge from large-scale 3D foundation models, opening up applications in surveillance and autonomous navigation.