R
Published on

CVPR 2026 — Face, Body & Biometrics

Face, Body & Biometrics

109 papers

1. EG-3DVG: Expression and Geometry Aware Grounding Decoder for 3D Visual Grounding

2. Computation and Communication Efficient Federated Unlearning via On-server Gradient Conflict Mitigation and Expression

3. Neural Field-Based 3D Surface Reconstruction of Microstructures from Multi-Detector Signals in Scanning Electron Microscopy

4. Cross-Modal Emotion Transfer for Emotion Editing in Talking Face Video

5. Inconsistency-aware Multimodal Schrodinger Bridge for Deepfake Localization

6. WildCap: Facial Albedo Capture in the Wild via Hybrid Inverse Rendering

7. All in One: Unifying Deepfake Detection, Tampering Localization, and Source Tracing with a Robust Landmark-Identity Watermark

8. Face2Scene: Using Facial Degradation as an Oracle for Diffusion-Based Scene Restoration

9. FHAvatar: Fast and High-Fidelity Reconstruction of Face-and-Hair Composable 3D Head Avatar from Few Casual Captures

10. One Model, Many Budgets: Elastic Latent Interfaces for Diffusion Transformers

11. X-AVDT: Audio-Visual Cross-Attention for Robust Deepfake Detection

12. CLEX: Complementary Label Exchange Learning for Noisy Facial Expression Recognition

13. NOWA: Null-space Optical Watermark for Invisible Capture Fingerprinting and Tamper Localization

14. FACE: A Face-based Autoregressive Representation for High-Fidelity and Efficient Mesh Generation

15. FVBench: Benchmarking Deepfake Video Detection Capability of Large Multimodal Models

16. ManifoldNeuS: Manifold-aware View Optimizability for Pose-Free Neural Surface Reconstruction

17. Adapting a Pre-trained Single-Cell Foundation Model to Spatial Gene Expression Generation from Histology Images

18. EmoThinker: Advancing Visual-Acoustic Emotion Analysis via Structural Token Selection and Chain-of-Thought Reasoning

19. OSMO: Open-vocabulary Self-eMOtion Tracking

20. Cross-Slice Knowledge Transfer via Masked Multi-Modal Heterogeneous Graph Contrastive Learning for Spatial Gene Expression Inference

21. Neural Gabor Splatting: Enhanced Gaussian Splatting with Neural Gabor for High-frequency Surface Reconstruction

22. Agent4FaceForgery: Multi-Agent LLM Framework for Realistic Face Forgery Detection

23. Plug-and-Play Incomplete Multi-View Clustering via Janus-Faced Affinity Learning with Topology Harmonization

24. DiffusionFF: A Diffusion-based Framework for Joint Face Forgery Detection and Fine-Grained Artifact Localization

25. DeepProtect: Proactive Face-Swapping Defense using Identity Blending and Attribute Distortion

26. Protego: User-Centric Pose-Invariant Privacy Protection Against Face Recognition-Induced Digital Footprint Exposure

27. MeshWeaver: Sparse-Voxel-Guided Surface Weaving for Autoregressive Mesh Generation

28. EmoTaG: Emotion-Aware Talking Head Synthesis on Gaussian Splatting with Few-Shot Personalization

29. SeeGroup: Multi-Layer Depth Estimation of Transparent Surfaces via Self-Determined Grouping

30. MMGait: Towards Multi-Modal Gait Recognition

31. DFD-HR: Generalizable Deepfake Detection via Hierarchical Routing Learning

32. MMFace-DiT: A Dual-Stream Diffusion Transformer for High-Fidelity Multimodal Face Generation

33. EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models

34. RecoverMark: Robust Watermarking for Localization and Recovery of Manipulated Faces

35. Distilling Unsigned Distance Function for Surface Reconstruction from 3D Gaussian Splatting

36. Diffusion-Based Makeup Transfer with Facial Region-Aware Makeup Features

37. MetaSpectra+: A Compact Broadband Metasurface Camera for Snapshot Hyperspectral+ Imaging

38. Representing 3D Faces with Learnable B-Spline Volumes

39. EmoStyle: Emotion-Driven Image Stylization

40. Frequency-domain Manipulation for Face Obfuscation

41. E3AD: An Emotion-Aware Vision-Language-Action Model for Human-Centric End-to-End Autonomous Driving

42. From Spots to Pixels: Dense Spatial Gene Expression Prediction from Histology Images

43. Attribute-Preserving Pseudo-Labeling for Diffusion-Based Face Swapping

44. Iris: Bringing Real-World Priors into Diffusion Model for Monocular Depth Estimation

45. MS^2Gait: A Multi-Scale Spatio-Temporal Fusion Network for LiDAR-based Gait Recognition

46. Pointer-CAD: Unifying B-Rep and Command Sequences via Pointer-based Edges & Faces Selection

47. Faithful Contouring: Near-Lossless 3D Voxel Representation Free from Iso-surface

48. Nano-EmoX: Unifying Multimodal Emotional Intelligence from Perception to Empathy

49. Real2Edit2Real: Generating Robotic Demonstrations via a 3D Control Interface

50. No Way To Steal My Face: Proactive Defense Against Identity-Preserving Personalized Generation

51. MVGGT: Multimodal Visual Geometry Grounded Transformer for Multiview 3D Referring Expression Segmentation

52. Pixels Don't Lie (But Your Detector Might): Bootstrapping MLLM-as-a-Judge for Trustworthy Deepfake Detection and Reasoning Supervision

53. Bridging Facial Understanding and Animation via Language Models

54. OMGTex: One-stage Multi-style Facial Texture Reconstruction without Geometry Guidance

55. HyperGait: Unleashing the Power of Parsing for Gait Recognition in the Wild via Hypergraph

56. TriDF: Evaluating Perception, Detection, and Hallucination for Interpretable DeepFake Detection

57. Cell-Type Prototype-Informed Neural Network for Gene Expression Estimation from Pathology Images

58. Text-guided Feature Disentanglement for Cross-modal Gait Recognition

59. Hearing the Room Through the Shape of the Drum: Modal-Guided Sound Recovery from Multi-Point Surface Vibrations

60. Face-Guided Sentiment Boundary Enhancement for Weakly-Supervised Temporal Sentiment Localization

61. From Pixel to Precision: Enhancing Handwritten Mathematical Expression Recognition with Image-Level Reward

62. BarbieGait: An Identity-Consistent Synthetic Human Dataset with Versatile Cloth-Changing for Gait Recognition

63. PC-Talk: Precise Facial Animation Control for Audio-Driven Talking Face Generation

64. HyperGaussians: High-Dimensional Gaussian Splatting for High-Fidelity Animatable Face Avatars

65. High-Fidelity Diffusion Face Swapping with ID-Constrained Facial Conditioning

66. CSF: Black-box Fingerprinting via Compositional Semantics for Text-to-Image Models

67. SIF: Semantically In-Distribution Fingerprints for Large Vision-Language Models

68. EventGait: Towards Robust Gait Recognition with Event Streams

69. Hermite Radial Basis Function for Surface Reconstruction via Differentiable Rendering

70. EmoDiffTalk: Emotion-aware Diffusion for Editable 3D Gaussian Talking Head

71. A Sanity Check for Multi-In-Domain Face Forgery Detection in the Real World

72. 4DSurf: High-Fidelity Dynamic Scene Surface Reconstruction

73. BeautyGRPO: Aesthetic Alignment for Face Retouching via Dynamic Path Guidance and Fine-Grained Preference Modeling

74. Unlocking Motion from Large Vision Models with a Semantic and Kinematic Duality for Gait Recognition

75. Registration-Free Learnable Multi-View Capture of Faces in Dense Semantic Correspondence

76. Beyond Missing Modalities: Hypergraph Conditioned Diffusion for Uncertainty-Aware Multimodal Emotion Recognition

77. 3D Gaussian Splatting with Self-Constrained Priors for High Fidelity Surface Reconstruction

78. PerformRecast: Expression and Head Pose Disentanglement for Portrait Video Editing

79. D^3FER: Dual Channel and Dual Branch Network for Robust Facial Expression Recognition under Dual Challenges

80. Harnessing Chain-of-Thought Reasoning in Multimodal Large Language Models for Face Anti-Spoofing

81. Goldilocks Test Sets for Face Verification

82. Investigating Self-Supervised Representations for Audio-Visual Deepfake Detection

83. Dynamic Label Noise Suppression with Optimal Teacher Pool for Facial Expression Recognition

84. Spatial Matters: Position-Guided 3D Referring Expression Segmentation

85. From Intuition to Investigation: A Tool-Augmented Reasoning MLLM Framework for Generalizable Face Anti-Spoofing

86. POLAR: A Portrait OLAT Dataset and Generative Framework for Illumination-Aware Face Modeling

87. Decoupling Bias, Aligning Distributions: Synergistic Fairness Optimization for Deepfake Detection

88. Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection

89. IrisFP: Adversarial-Example-based Model Fingerprinting with Enhanced Uniqueness and Robustness

90. Beyond [CLS] Token: Query-Driven Token-Level Forgery Purification for Generalizable Deepfake Detection

91. FaceCam: Portrait Video Camera Control via Scale-Aware Conditioning

92. IP-Adapter Is All You Need: Towards Fine-Tuning-Free Diffusion-Based Talking Face Generation

93. IDperturb: Enhancing Variation in Synthetic Face Generation via Angular Perturbations

94. UniMERNet: A Universal Network for Real-World Mathematical Expression Recognition

95. Tutor-Student Reinforcement Learning: A Dynamic Curriculum for Robust Deepfake Detection

96. ImmerIris: A Large-Scale Dataset and Benchmark for Off-Axis and Unconstrained Iris Recognition in Immersive Applications

97. Region-Aware Instance Consistency Learning for Micro-Expression Recognition

98. TESSERA: Temporal Embeddings of Surface Spectra for Earth Representation and Analysis

99. RDFace: A Benchmark Dataset for Rare Disease Facial Image Analysis under Extreme Data Scarcity and Phenotype-Aware Synthetic Generation

100. Neu-PiG: Neural Preconditioned Grids for Fast Dynamic Surface Reconstruction on Long Sequences

101. Iris: Integrating Language into Diffusion-based Monocular Depth Estimation

102. VIRO: Robust and Efficient Neuro-Symbolic Reasoning with Verification for Referring Expression Comprehension

103. SketchFaceGS: Real-Time Sketch-Driven Face Editing and Generation with Gaussian Splatting

104. DeepfakeImpact: A Two-Stage Benchmark with Real-World Impact in Deepfake Detection

105. PortraitDirector: A Hierarchical Disentanglement Framework for Controllable and Real-time Facial Reenactment

106. SAQN: Semantic-based Adaptive Query Network for 3D Referring Expression Segmentation

107. Unleashing Vision-Language Semantics for Deepfake Video Detection

108. Editprint: General Digital Image Forensics via Editing Fingerprint with Self-Augmentation Training

109. Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality