mlsanityData to 7 Oct 2026

CAUSAL3D: A Comprehensive Benchmark for Causal Learning from Visual Data

arXiv 2503.04852 ↗First posted 6 Mar 2025cs.CV cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

True intelligence hinges on the ability to uncover and leverage hidden causal relations. Despite significant progress in AI and computer vision (CV), there remains a lack of benchmarks for assessing models' abilities to infer latent causality from complex visual data. In this paper, we introduce textscCausal3D, a novel and comprehensive benchmark that integrates structured data (tables) with corresponding visual representations (images) to evaluate causal reasoning. Designed within a systematic framework, Causal3D comprises 19 3D-scene datasets capturing diverse causal relations, views, and backgrounds, enabling evaluations across scenes of varying complexity. We assess multiple state-of-the-art methods, including classical causal discovery, causal representation learning, and large/vision-language models (LLMs/VLMs). Our experiments show that as causal structures grow more complex without prior knowledge, performance declines significantly, highlighting the challenges even advanced methods face in complex causal scenarios. Causal3D serves as a vital resource for advancing causal reasoning in CV and fostering trustworthy AI in critical domains.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 39 of its 53 references that are in the map. First posted on arXiv 6 Mar 2025.

Builds on

39 of 53 references.

References · 39

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  4. 2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 745
  5. 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 479
  6. 2023Causal Reasoning and Large Language Models: Opening a New Frontier for Causalitycited by 348
  7. 2019DAG-GNN: DAG Structure Learning with Graph Neural Networkscited by 329
  8. 2021Self-Supervised Learning with Data Augmentations Provably Isolates Content from Stylecited by 308
  9. 2019Causality for Machine Learningcited by 242
  10. 2017Detecting causal associations in large nonlinear time series datasetscited by 240
  11. 2019Gradient-Based Neural DAG Learningcited by 227
  12. 2021Contrastive Learning Inverts the Data Generating Processcited by 220
27 more
  1. 2013CAM: Causal additive models, high-dimensional order search and penalized regressioncited by 175
  2. 2022Revisiting Weakly Supervised Pre-Training of Visual Perception Modelscited by 116
  3. 2021Causal Attention for Vision-Language Taskscited by 111
  4. 2022Score matching enables causal discovery of nonlinear additive noise modelscited by 108
  5. 2013Learning Equivalence Classes of Bayesian Networks Structurescited by 75
  6. 2020Weakly Supervised Disentangled Generative Causal Representation Learningcited by 67
  7. 2022Diffusion Models for Causal Discovery via Topological Orderingcited by 64
  8. 2023Physion++: Evaluating Physical Scene Understanding that Requires Online Inference of Different Physical Propertiescited by 53
  9. 2024Efficient Causal Graph Discovery Using Large Language Modelscited by 51
  10. 2024Vision-and-Language Navigation via Causal Learningcited by 51
  11. 2020CausalVAE: Structured Causal Disentanglement in Variational Autoencodercited by 47
  12. 2020CRAFT: A Benchmark for Causal Reasoning About Forces and inTeractionscited by 44
  13. 2024Causal Inference with Large Language Model: A Surveycited by 31
  14. 2022Causal Reasoning Meets Visual Representation Learning: A Prospective Studycited by 24
  15. 2024Causality for Large Language Modelscited by 24
  16. 2023Learning Causally Disentangled Representations via the Principle of Independent Causal Mechanismscited by 14
  17. 2020Improving Certified Robustness via Statistical Learning with Logical Reasoningcited by 12
  18. 2021Causal-TGAN: Generating Tabular Data Using Causal Generative Adversarial Networkscited by 12
  19. 2022Deep Causal Learning: Representation, Discovery and Inferencecited by 11
  20. 2023CLEVRER-Humans: Describing Physical and Causal Events the Human Waycited by 11
  21. 2023Causal-CoG: A Causal-Effect Look at Context Generation for Boosting Multi-modal Language Modelscited by 10
  22. 2024Causality for Tabular Data Synthesis: A High-Order Structure Causal Benchmark Frameworkcited by 7
  23. 2022Causal Discovery and Knowledge Injection for Contestable Neural Networks (with Appendices)cited by 6
  24. 2023Boosting Synthetic Data Generation with Effective Nonlinear Causal Discoverycited by 4
  25. 2023Causally Disentangled Generative Variational AutoEncodercited by 2
  26. 2024Functional Linear Non-Gaussian Acyclic Model for Causal Discoverycited by 2
  27. 2024Do Large Language Models Show Biases in Causal Learning?cited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 3.

7 papers.

  1. 2025CausalVLBench: Benchmarking Visual Causal Reasoning in Large Vision-Language Modelscited by 7
  2. 2025Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AIcited by 3
  3. 2025CausalVerse: Benchmarking Causal Representation Learning with Configurable High-Fidelity Simulationscited by 3
  4. 2026Causal Scaffolding for Physical Reasoning: A Benchmark for Causally-Informed Physical World Understanding in VLMscited by 3
  5. 2025Distilling Counterfactual Reasoning from Language to Vision: Causal Graph Guided Post-Training for Video Understandingcited by 2
  6. 2026From Prompts to Tokens: Internalizing Causal Supervision in Vision-Language Model for Multi-Image Causal Reasoningcited by 0
  7. 2026CCRV-Bench: Constraint-Based Evaluation of Causal Reasoning in Vision-Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025CauSight: Learning to Supersense for Visual Causal Discovery
  2. 2025InfoCausalQA:Can Models Perform Non-explicit Causal Reasoning Based on Infographic?
  3. 2026CausalSplat: Towards Comprehensive Hierarchical Reasoning in 3D Gaussian Splatting
  4. 2025ISO-Bench: Benchmarking Multimodal Causal Reasoning in Visual-Language Models through Procedural Plans
  5. 2026CausalSpatial: A Benchmark for Object-Centric Causal Spatial Reasoning
  6. 2026CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answering
  7. 2024Multimodal Causal Reasoning Benchmark: Challenging Vision Large Language Models to Discern Causal Links Across Modalities
  8. 2025Causal Reasoning Elicits Controllable 3D Scene Generation