Exploring Easy Boosts for Lidar Semantic Scene Completion

• URL: http://arxiv.org/abs/2606.03992v1
• Date: Tue, 02 Jun 2026 17:59:59 GMT
• Title: Exploring Easy Boosts for Lidar Semantic Scene Completion
• Abstract summary: "Free lunch" strategies to boost the performance of lidar semantic scene completion (SSC) without requiring complex architectural redesigns.<n>We first demonstrate that endowing input point clouds with semantic pseudo-labels from off-the-shelf segmentors significantly improves the performance of existing architectures.
• Score: 61.665449818739155
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper investigates "free lunch" strategies to boost the performance of lidar semantic scene completion (SSC) without requiring complex architectural redesigns. We first demonstrate that endowing input point clouds with semantic pseudo-labels from off-the-shelf segmentors significantly improves the performance of existing architectures. By evaluating these models against an oracle, we establish that high-quality semantic priors are a primary driver of mIoU gains. Furthermore, we equip the input lidar scan with visibility information that distinguishes between empty and unknown spaces, which provides a secondary performance boost across the tested architectures. Using these simple enhancements, we observe that older models remain competitive with state-of-the-art systems, and can even outperform them. Our code is available at https://github.com/astra-vision/SSC-Priors.

Related papers

• SSC-Priors: Exploring Semantic and Visibility Priors to Boost Lidar Semantic Scene Completion [61.665449818739155]
  This paper investigates easy strategies to boost the performance of existing networks for lidar semantic scene completion (SSC)<n>We use semantic pseudo-labels and sensor visibility information to improve existing approaches.<n>We show that endowing input point clouds with semantic pseudo-labels from off-the-shelf segmenters significantly improves the performance of existing SSC models.
  arXiv  Detail & Related papers  (2026-09-15T16:37:46Z)
• Semantic Generative Tuning for Unified Multimodal Models [62.18894352635965]
  Unified multimodal models (UMMs) strive to consolidate visual understanding and visual generation within a single architecture.<n> prevailing training paradigms independently optimize understanding via sparse text signals and generation through dense pixel objectives.<n>This work presents the first systematic investigation into generative post-training, where we formulate hierarchical visual tasks as generative proxies to bridge the isolation in UMMs.
  arXiv  Detail & Related papers  (2026-05-18T17:46:46Z)
• ReME: A Data-Centric Framework for Training-Free Open-Vocabulary Segmentation [18.666044903856363]
  Training-free open-vocabulary semantic segmentation (OVS) aims to segment images given a set of arbitrary textual categories without costly model fine-tuning.<n>We introduce a data-quality-oriented framework, comprising a data pipeline to construct a reference set with well-paired segment-text embeddings and a simple similarity-based retrieval.<n>Our method outperforms all existing training-free OVS approaches, highlighting the importance of data-centric design for advancing OVS without training.
  arXiv  Detail & Related papers  (2025-06-26T13:22:03Z)
• Semi-supervised Semantic Segmentation with Multi-Constraint Consistency Learning [81.02648336552421]
  We propose a Multi-Constraint Consistency Learning approach to facilitate the staged enhancement of the encoder and decoder.<n>Self-adaptive feature masking and noise injection are designed in an instance-specific manner to perturb the features for robust learning of the decoder.<n> Experimental results on Pascal VOC2012 and Cityscapes datasets demonstrate that our proposed MCCL achieves new state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-03-23T03:21:33Z)
• Learning and Evaluating Hierarchical Feature Representations [3.770103075126785]
  We propose a novel framework, Hierarchical Composition of Orthogonal Subspaces (Hier-COS)<n>Hier-COS learns to map deep feature embeddings into a vector space that is, by design, consistent with the structure of a given taxonomy tree.<n>We demonstrate that Hier-COS achieves state-of-the-art hierarchical performance across all the datasets while simultaneously beating top-1 accuracy in all but one case.
  arXiv  Detail & Related papers  (2025-03-10T20:59:41Z)
• Pay Attention to Your Neighbours: Training-Free Open-Vocabulary Semantic Segmentation [19.20874993309959]
  vision-language foundation models, such as CLIP, have showcased remarkable effectiveness in numerous zero-shot image-level tasks. We propose a baseline for training-free OVSS, termed Neighbour-Aware CLIP (NACLIP) Our method enforces localization of patches in the self-attention of CLIP's vision transformer which, despite being crucial for dense prediction tasks, has been overlooked in the OVSS literature.
  arXiv  Detail & Related papers  (2024-04-12T01:08:04Z)
• OMH: Structured Sparsity via Optimally Matched Hierarchy for Unsupervised Semantic Segmentation [69.37484603556307]
  Un Semantic segmenting (USS) involves segmenting images without relying on predefined labels. We introduce a novel approach called Optimally Matched Hierarchy (OMH) to simultaneously address the above issues. Our OMH yields better unsupervised segmentation performance compared to existing USS methods.
  arXiv  Detail & Related papers  (2024-03-11T09:46:41Z)
• CLIP Brings Better Features to Visual Aesthetics Learners [14.351572852317558]
  Image Aesthetics Assessment (IAA) is a challenging task due to its subjective nature and expensive manual annotations.<n>Recent large-scale vision-language models, such as Contrastive Language-Image Pre-training (CLIP), have shown their promising representation capability for various downstream tasks.<n>We propose a two-phase CLIP-based Semi-supervised Knowledge Distillation paradigm, aiming to learn a lightweight IAA model while leveraging CLIP's strong generalization capability.
  arXiv  Detail & Related papers  (2023-07-28T16:00:21Z)
• ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation [23.207191521477654]
  We investigate if we could make the self-training -- a simple but popular framework -- work better for semi-supervised segmentation. We propose an advanced self-training framework (namely ST++) that performs selective re-training via selecting and prioritizing the more reliable unlabeled images. As a result, the proposed ST++ boosts the performance of semi-supervised model significantly and surpasses existing methods by a large margin on the Pascal VOC 2012 and Cityscapes benchmark.
  arXiv  Detail & Related papers  (2021-06-09T14:18:32Z)
• Prior Guided Feature Enrichment Network for Few-Shot Segmentation [64.91560451900125]
  State-of-the-art semantic segmentation methods require sufficient labeled data to achieve good results. Few-shot segmentation is proposed to tackle this problem by learning a model that quickly adapts to new classes with a few labeled support samples. Theses frameworks still face the challenge of generalization ability reduction on unseen classes due to inappropriate use of high-level semantic information.
  arXiv  Detail & Related papers  (2020-08-04T10:41:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.