# Rewis3d: Reconstruction Improves Weakly-Supervised Semantic Segmentation

arXiv: https://arxiv.org/abs/2603.06374 · HTML: https://mlsanity.com/paper/2603.06374/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 39 of its 52 references that are in the map.
- First posted on arXiv 6 Mar 2026.

## Builds on (most cited first, 30 of 39)

- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [Point Transformer V3: Simpler, Faster, Stronger](https://mlsanity.com/paper/2312.10035/) (2023)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion](https://mlsanity.com/paper/2410.03825/) (2024)
- [ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1604.05144/) (2016)
- [MapAnything: Universal Feed-Forward Metric 3D Reconstruction](https://mlsanity.com/paper/2509.13414/) (2025)
- [Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach](https://mlsanity.com/paper/1703.08448/) (2017)
- [2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds](https://mlsanity.com/paper/2207.04397/) (2022)
- [On Regularized Losses for Weakly-supervised CNN Segmentation](https://mlsanity.com/paper/1803.09569/) (2018)
- [Normalized Cut Loss for Weakly-supervised CNN Segmentation](https://mlsanity.com/paper/1804.01346/) (2018)
- [Scribble-Supervised LiDAR Semantic Segmentation](https://mlsanity.com/paper/2203.08537/) (2022)
- [Your ViT is Secretly an Image Segmentation Model](https://mlsanity.com/paper/2503.19108/) (2025)
- [Indoor Semantic Segmentation using depth information](https://mlsanity.com/paper/1301.3572/) (2013)
- [Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentation](https://mlsanity.com/paper/2203.10739/) (2022)
- [GrowSP: Unsupervised Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/2305.16404/) (2023)
- [From CNN to Transformer: A Review of Medical Image Segmentation Models](https://mlsanity.com/paper/2308.05305/) (2023)
- [Weakly-Supervised Semantic Segmentation with Image-Level Labels: from Traditional Models to Foundation Models](https://mlsanity.com/paper/2310.13026/) (2023)
- [Image Understands Point Cloud: Weakly Supervised 3D Semantic Segmentation via Association Learning](https://mlsanity.com/paper/2209.07774/) (2022)
- [SparseDet: Improving Sparsely Annotated Object Detection with Pseudo-positive Mining](https://mlsanity.com/paper/2201.04620/) (2022)
- [Label Cleaning Multiple Instance Learning: Refining Coarse Annotations on Single Whole-Slide Images](https://mlsanity.com/paper/2109.10778/) (2021)
- [3D Weakly Supervised Semantic Segmentation with 2D Vision-Language Guidance](https://mlsanity.com/paper/2407.09826/) (2024)
- [Urban Scene Semantic Segmentation with Low-Cost Coarse Annotation](https://mlsanity.com/paper/2212.07911/) (2022)
- [3D Guided Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2012.00242/) (2020)

## Abstract (arXiv)

We present Rewis3d, a framework that leverages recent advances in feed-forward 3D reconstruction to significantly improve weakly supervised semantic segmentation on 2D images. Obtaining dense, pixel-level annotations remains a costly bottleneck for training segmentation models. Alleviating this issue, sparse annotations offer an efficient weakly-supervised alternative. However, they still incur a performance gap. To address this, we introduce a novel approach that leverages 3D scene reconstruction as an auxiliary supervisory signal. Our key insight is that 3D geometric structure recovered from 2D videos provides strong cues that can propagate sparse annotations across entire scenes. Specifically, a dual student-teacher architecture enforces semantic consistency between 2D images and reconstructed 3D point clouds, using state-of-the-art feed-forward reconstruction to generate reliable geometric supervision. Extensive experiments demonstrate that Rewis3d achieves state-of-the-art performance in sparse supervision, outperforming existing approaches by 2-7% without requiring additional labels or inference overhead.