Cover Image

Three Pillars improving Vision Foundation Model Distillation for Lidar

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Puy, Gilles, Gidaris, Spyros, Boulch, Alexandre, Siméoni, Oriane, Sautier, Corentin, Pérez, Patrick, Bursuc, Andrei, Marlet, Renaud
Format:	Preprint
Published:	2023
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MILAN: Milli-Annotations for Lidar Semantic Segmentation
by: Samet, Nermin, et al.
Published: (2024)

Is clustering enough for LiDAR instance segmentation? A state-of-the-art training-free baseline
by: Sautier, Corentin, et al.
Published: (2025)

UNIT: Unsupervised Online Instance Segmentation through Time
by: Sautier, Corentin, et al.
Published: (2024)

Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Survey
by: Siméoni, Oriane, et al.
Published: (2023)

Vanilla ViT for Automotive Point Cloud Semantic Segmentation
by: Puy, Gilles, et al.
Published: (2026)

OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networks
by: Sirko-Galouchenko, Sophia, et al.
Published: (2024)

Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillation
by: Vobecky, Antonin, et al.
Published: (2022)

LiDPM: Rethinking Point Diffusion for Lidar Scene Completion
by: Martyniuk, Tetiana, et al.
Published: (2025)

Valeo4Cast: A Modular Approach to End-to-End Forecasting
by: Xu, Yihong, et al.
Published: (2024)

IGLOSS: Image Generation for Lidar Open-vocabulary Semantic Segmentation
by: Samet, Nermin, et al.
Published: (2026)

SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptation
by: Michele, Björn, et al.
Published: (2023)

POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images
by: Vobecky, Antonin, et al.
Published: (2024)

MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments
by: Gidaris, Spyros, et al.
Published: (2023)

Test-time Contrastive Concepts for Open-world Semantic Segmentation with Vision-Language Models
by: Wysoczańska, Monika, et al.
Published: (2024)

Improving Multimodal Distillation for 3D Semantic Segmentation under Domain Shift
by: Michele, Björn, et al.
Published: (2025)

LOSC: LiDAR Open-voc Segmentation Consolidator
by: Samet, Nermin, et al.
Published: (2025)

Train Till You Drop: Towards Stable and Robust Source-free Unsupervised 3D Domain Adaptation
by: Michele, Björn, et al.
Published: (2024)

Driving on Registers
by: Kirby, Ellington, et al.
Published: (2026)

CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentation
by: Wysoczańska, Monika, et al.
Published: (2023)

No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen Representations
by: Simoncini, Walter, et al.
Published: (2024)

DIP: Unsupervised Dense In-Context Post-training of Visual Representations
by: Sirko-Galouchenko, Sophia, et al.
Published: (2025)

Boosting Visual Instruction Tuning with Self-Supervised Guidance
by: Sirko-Galouchenko, Sophia, et al.
Published: (2026)

LOGen: Toward Lidar Object Generation by Point Diffusion
by: Kirby, Ellington, et al.
Published: (2024)

VaViM and VaVAM: Autonomous Driving through Video Generative Modeling
by: Bartoccioni, Florent, et al.
Published: (2025)

Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning
by: Venkataramanan, Shashanka, et al.
Published: (2025)

3D sans 3D Scans: Scalable Pre-training from Video-Generated Point Clouds
by: Yamada, Ryousuke, et al.
Published: (2025)

Coevolving Representations in Joint Image-Feature Diffusion
by: Kouzelis, Theodoros, et al.
Published: (2026)

Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction
by: Karypidis, Efstathios, et al.
Published: (2026)

LLM-wrapper: Black-Box Semantic-Aware Adaptation of Vision-Language Models for Referring Expression Comprehension
by: Cardiel, Amaia, et al.
Published: (2024)

SuperQuadricOcc: Real-Time Self-Supervised Semantic Occupancy Estimation with Superquadric Volume Rendering
by: Hayes, Seamie, et al.
Published: (2025)

sim2art: Accurate Articulated Object Modeling from a Single Video using Synthetic Training Data Only
by: Artykov, Arslan, et al.
Published: (2025)

Revisiting [CLS] and Patch Token Interaction in Vision Transformers
by: Marouani, Alexis, et al.
Published: (2026)

Domain Adaptation with a Single Vision-Language Embedding
by: Fahes, Mohammad, et al.
Published: (2024)

Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers
by: Karypidis, Efstathios, et al.
Published: (2025)

SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers
by: Kakogeorgiou, Ioannis, et al.
Published: (2023)

DINO-Foresight: Looking into the Future with DINO
by: Karypidis, Efstathios, et al.
Published: (2024)

Multi-Token Prediction Needs Registers
by: Gerontopoulos, Anastasios, et al.
Published: (2025)

Boosting Generative Image Modeling via Joint Image-Feature Synthesis
by: Kouzelis, Theodoros, et al.
Published: (2025)

CLIP's Visual Embedding Projector is a Few-shot Cornucopia
by: Fahes, Mohammad, et al.
Published: (2024)

A Simple Recipe for Language-guided Domain Generalized Segmentation
by: Fahes, Mohammad, et al.
Published: (2023)