AI Paper Atlas

Research map / 3D vision / 3D generation

Splat and Distill: Augmenting Teachers with Feed-Forward 3D Reconstruction For 3D-Aware Distillation

David Shavin, Sagie Benaim

ICLR 2026 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add semantic blending (ablation)Splat and Distill · ScanNet++ depth (ViT-S)RMSE: 0.3435 -> 0.3299Improved
add semantic blending (ablation)Splat and Distill · ScanNet++ segmentation (ViT-S)mIoU: 30.99 -> 31.78Improved
add mask-aware upscaling instead of bilinear (ablation)Splat and Distill · ScanNet++ depth (ViT-S)RMSE: 0.3309 -> 0.3299Improved
use DINO distillation loss instead of cosine loss (ablation)Splat and Distill · ScanNet++ depth (ViT-S)RMSE: 0.3310 -> 0.3299Improved
use EMA-updated teacher instead of frozen teacher (ablation)Splat and Distill · ScanNet++ depth (ViT-S)RMSE: 0.3444 -> 0.3299Improved
render to novel target view instead of context views (ablation)Splat and Distill · ScanNet++ depth (ViT-S)RMSE: 0.3332 -> 0.3299Improved
render to novel target view instead of context views (ablation)Splat and Distill · ScanNet++ segmentation (ViT-S)mIoU: 32.08 -> 31.78Hurt
use manual masks instead of SAM masks (ablation)Splat and Distill · ScanNet++ depth (ViT-S)RMSE: 0.3328 -> 0.3299Improved
use student-teacher distillation instead of direct feature rendering loss (ablation)Splat and Distill · ScanNet++ depth (ViT-S)RMSE: 0.3430 -> 0.3299Improved
add EMA teacher, mask-aware upscaling and blending to basic variant (ablation)Splat and Distill · ScanNet++ depth (ViT-S)RMSE: 0.3520 -> 0.3299Improved
use Splat and Distill instead of Fit3D (ViT-S)Fit3D · ScanNet++ depth (ViT-S)RMSE: 0.3506 -> 0.3299Improved
use Splat and Distill instead of Fit3D (ViT-B)Fit3D · ScanNet++ segmentation (ViT-B)mIoU: 34.85 -> 34.07Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy