Technical Program
Tentative Program
Last Updated: 20 November 2026, 18:24 SGT
Presentation order in each session is subject to change.
Day 1 – Sunday, 13 December 2026
Tutorial 1: Rate-Distortion Optimized 3D and 4D Gaussian Splatting: Representations, Processing, and Recent Advances
Speakers
- Jui-Chiu (Rachel) Chiang (National Chung Cheng University, TW)
- Nantheera (Pui) Anantrasirichai (University of Bristol, UK)
- Fan (Aaron) Zhang (University of Bristol, UK)
Tutorial 2: From Visual Signals to Multimodal Intelligence: Sensing, Representation, and Reasoning
Speakers
- Zeyu Xiao (National University of Singapore, SG)
- Rui Zhao (Nanyang Technological University, SG)
- Zhuoyuan Li (The Hong Kong Polytechnic University (PolyU), HK)
Tutorial 3: Neural Spatial Computing: Geometric Modeling and Representation Learning
Speakers
- Junhui Hou (City University of Hong Kong, HK)
Tutorial 4: Preference-Aligned Generative Low-level Visual Signal Processing, Compression and Quality Assessment
Speakers
- Xin Li (University of Science and Technology of China, CN)
- Guo Lu (Shanghai Jiao Tong University, CN)
- Xin Jin (Eastern Institute of Technology, Ningbo, CN)
- Zhibo Chen (University of Science and Technology of China, CN)
Tutorial 5: Efficient Learning-Based Compression Models: From Visual Data to Broader Modalities
Speakers
- Li Song (Shanghai Jiao Tong University, CN)
- Chuanmin Jia (Peking University, CN)
- Zhengxue Cheng (Shanghai Jiao Tong University, CN)
- Houqiang Li (University of Science and Technology of China (USTC), CN)
Tutorial 6: Secure Media Authentication in Practice: Digitally Signed Content with H.274/VSEI, Provenance with C2PA and Open-Source Tooling
Speakers
- Benjamin Bross (Fraunhofer Heinrich Hertz Institut, DE)
- Karsten Sühring (Fraunhofer Heinrich Hertz Institut, DE)
- Stefan Pham (Fraunhofer Institute for Open Communication Systems, DE)
- Stephan Steglich (Fraunhofer Institute for Open Communication Systems, DE)
Day 2 – Monday, 14 December 2026
Keynote 1: From Seamless to Trustworthy Visual Communication: The Case of JPEG Trust
Keynote 2: Perceptual AI – Video Coding for Machines
Oral Session 1: S1 Learned Image Compression I
-
#165 Safe Adaptive Quantization for Ultra-Low-Bitrate Generative Image Compression
Authors
-
#101 Joint Activation and Weight Quantization for Learned Image Compression
Authors
-
#23 Multi-scale Image Representation Compression
Authors
-
#51 UniDC: Compression-Aware One-Step Diffusion for Efficient Variable-Rate Image Compression
Authors
-
#95 Learning Visual Feature Representations for Perception-Oriented Learned Image Compression
Authors
Oral Session 2: S2 Multimodal Perception and Grounding
-
#134 LLM-Guided Explicit Geometric Understanding for 3D Visual Grounding
Authors
-
#62 MDSL: Modality-Decoupled Synergistic Learning for Open-Vocabulary Audio-Visual Event Localization
Authors
-
#167 A³-Ground: Attribute-Aware Adaptation for Fine-Grained Open-Vocabulary Vehicle Grounding
Authors
-
#5 MultiPose: Unified Full-Body Multimodal Fusion via xLSTM-Based Lightweight Temporal Modeling
Authors
-
#29 CAPNet: Cross-Attentive Feature Pyramid Network for Cross-View Geo-Localization
Authors
Oral Session 3: S3 Learned Video Compression and Neural Video Representation
-
#77 Dense-Prior-Guided Generative Video Compression
Authors
-
#76 VRAE: Unified Video Reconstruction and Generation with Video Representation Autoencoders
Authors
-
#49 DEVC: Diffusion-Enhanced Video Compression for Ultra-Low Bitrates
Authors
-
#74 Affine-Aligned Atlas for Canonical Gaussian Construction in Video Representation
Authors
-
#231 CG-NeRV: Coarse-to-fine Grid-Based Neural Representation for Video Compression
Authors
Oral Session 4: S4 Representation Learning and Efficient Vision Models
-
#233 Dissecting Representation Structure in Vision Transformers: A Rigorous Architectural Study
Authors
-
#73 Resolution-Flexible Decoding for Hybrid Neural Video Representations
Authors
-
#2 Prompt-Encoding-based Dataset Distillation with Public Text-to-Image Models
Authors
-
#15 Bidirectional Motion Fusion and Hybrid Run-Length Coding for Dynamic Point Cloud Compression
Authors
-
#63 Post-Training Quantization for Diffusion Transformers via Temporal Activation Grouping and Weight Distribution Categorization
Authors
Oral Session 5: S5 Video Coding Tools and Encoder Optimization
-
#59 Can LLMs Design Video Coding Tools? A Case Study on Planar Mode
Authors
-
#204 In-Depth Rate-Distortion Analysis of Video Encoding Algorithms with Reference Encoder
Authors
-
#94 One-Vector LoRA Adaptation for Content-Adaptive Neural Video Post-Filtering
Authors
-
#173 NC-STDF: Spatio-Temporal Deformable Fusion for Neural Video Coding Quality Enhancement
Authors
-
#69 Analysis and Prediction of Energy Consumption for Parallelized SVT-AV1 Encoding
Authors
Oral Session 6: S6 3D Scene Representation, Rendering and Perception
-
#216 3D Gaussian Splatting with Polarization-Guided Normal Constraints
Authors
-
#35 Impact of Attribute Distortions on Perceptual Quality of 3D Gaussian Splatting
Authors
-
#39 Event-Guided Inverse Optimization of 3D Gaussian Splatting with Known Trajectories: Stabilizing Training via APS Photometric Supervision
Authors
-
#218 Perceptual 3D Gaussian Splatting with 3D-Anchored Saliency Features
Authors
-
#98 Rendering Distortion Modeling for Video-Based 3D Gaussian Splatting Compression
Authors
Poster Session 1: P1 Image/Video/3D Coding and Streaming
-
#34 Template-Residual Bias Compensation for Fusion-Based Luma and Chroma Prediction in Video Coding
Authors
-
#79 Invisible-Region Preprocessing for Efficient Compression of Videos with Alpha Channel
Authors
-
#161 On the Formulation of Template-Adaptive Intra Prediction Models
Authors
-
#184 When Motion Flow Collapses: Global Motion Factorization for Efficient Neural Video Coding
Authors
-
#190 FALCON: Frequency-Aware Lightweight Convolutional Coding for Face Video Compression
Authors
-
#197 Are NeRV Decoders Overprovisioned? A Stage-Wise Study of Compute Redundancy in Neural Video Representations
Authors
-
#41 Live HTJ2K in the Browser: WebAssembly Decoding of RFC 9828 over WebTransport
Authors
-
#192 Rate-Quality-Energy Convex Hull for High Dynamic Range Adaptive Video Streaming
Authors
-
#46 Jointly 2D and 3D Geometry Quality Enhancement for Video-Based Point Cloud Compression (V-PCC)
Authors
-
#91 Efficient HAC: Enhanced Context Modeling for 3D Gaussian Splatting Compression
Authors
-
#103 Enhancing Compresison Efficiency of Gaussian Splatting via Flexible Pixel mapping
Authors
-
#96 Improved Training-Free Simplification for Planar-Based Gaussian Splatting
Authors
-
#158 Efficient Quality Controller for Video Encoding
Authors
-
#164 Bitrate Ladder Analysis for UHD Adaptive Streaming: From AVC to AV2
Authors
-
#239 Real-Time Implementation of End-to-End Neural-Network Decoder for Videos
Authors
-
#242 Demo: Digital Semantic Communications Based on Generative Semantic Error Correction
Authors
-
#176 Bitrate Tradeoff Between Geometry and Color Attributes for Point Cloud Coding
Authors
-
#241 Sports Tournament Management System
Authors
-
#243 SafeRecall: An Integrated Product Traceability and Automated Batch Recall Management System
Authors
Day 3 – Tuesday, 15 December 2026
Keynote 3: Beyond Scores: Toward Evidence-Grounded, Generalizable Visual Quality Assessment with LMMs
Keynote 4: Embodied Intelligent Perception and Manipulation
Oral Session 7: S7 Video Streaming and Delivery
-
#189 LoResNet: Light Codec-Aware Downscaling via Latent Distillation for Real-Time ABR Streaming
Authors
-
#106 Frequency-aware Object--Clutter Query Re-ranking for Tiny Object Detection
Authors
-
#111 RoboST: Task-Oriented Sim-to-Real Visual Adaptation for Robotic Manipulation
Authors
-
#50 VC-1K: A Diverse Video Test Set for Real-Time Communication
Authors
-
#33 Spatially Separated Timestamp Encoding for Non-Intrusive Latency Fingerprinting in Video Transmission Pipelines
Authors
Oral Session 8 (Special Session): S8 SS: Lenslet Video Coding — Standardization, Compression, and Processing for Immersive Light Field Media
-
#171 Advancements in MPEG Lenslet Video Coding
Authors
-
#217 Optimization of Edge Pixel Prediction Vectors for Codec-agnostic Lenslet Video Coding
Authors
-
#152 RealDynLFV: A Large-Parallax Benchmark for Real-World Dynamic Light Field Video
Authors
-
#187 Pleno-PSNR: A Micro-Lens-Aware Evaluation Metric for Lenslet Images
Authors
-
#228 Selective View-Dependent Patch Size Estimation for Rendering from Lenslet Images
Authors
Oral Session 9: S9 3D Gaussian Splatting: Compression and Streaming
-
#84 Real-Time Viewport-Adaptive Rate Control of Dynamic 3D Gaussian Splatting
Authors
-
#157 QoE-Driven Adaptive 3D Scene Transmission with Multi-Layered Sparse Voxel Rasterization
Authors
-
#114 Codec-Compatible Learned Compression for 3D Gaussian Splatting
Authors
-
#100 Non-Reference Lightweight Pruning for 3D Gaussian Splatting Coding with G-PCC
Authors
-
#86 TileSlim: Rendering-Cost-Aware Pruning for Efficient Rendering of 3D Gaussian Splatting
Authors
Oral Session 10: S10 Visual Quality Assessment and Enhancement
-
#120 Saliency Bias in Image Editing Quality Assessment
Authors
-
#154 WebSal-VLM: A Large Webpage Image Dataset and Vision-Language Model for Saliency Prediction
Authors
-
#68 SVBI-OVQA: Saliency-Based Viewport-Driven Bi-LSTM Network for No-Reference Omnidirectional Video Quality Assessment
Authors
-
#22 FreqWarp: Frequency-Decoupled Latent Warping for Training-Free Video Diffusion Restoration
Authors
-
#175 SADA: Difficulty-Aware, Region-Adaptive Low-Light Image Enhancement
Authors
Poster Session 2: P2 3D Vision, Quality, Restoration and Security
-
#21 Reflection-Aware Dynamic Gaussian Reconstruction for Water-Surface Scenes
Authors
-
#27 Geometry-Detail Enhanced 3D Gaussian Splatting Head Modeling via Global-Local Hybrid Feature Aggregation
Authors
-
#67 Slice-Based Feature Learning for Single-View 3D Reconstruction
Authors
-
#71 Annotation-Free 3D Gaussian ROI Extraction via Language-Grounded Multi-View Voting
Authors
-
#198 GSplatEdit3D: Learning Editable 3D Gaussian Scene Representations via Structured Latent Spaces
Authors
-
#209 Dynamic HyBiR: Explicit and Storage-Compact Data Representation for Dynamic NeRF
Authors
-
#6 Multi-Task Collaborative Vision-Language Correspondence Network for Blind Quality Assessment of AI-Generated Omnidirectional Images
Authors
-
#117 TriSK-RAG: Tri-attribute Structured-Knowledge RAG for Task-aware Visual Quality Comparison
Authors
-
#206 Super-Resolution Based on Graph Algorithm Unrolling for 4D Light Field Densification
Authors
-
#57 Grounding Text-Generated Motion for Object-Aware Avatar Interaction in Extended Reality
Authors
-
#118 3D Gaussian Splatting Rendering Performance Trade-offs on the Meta Quest 3
Authors
-
#149 Private Audio Communication by using Animated Portable Network Graphics
Authors
-
#214 Semantic Protection for CLIP Image Embeddings with Hierarchical Access Control
Authors
-
#223 Joint Architecture-Token-Bitwidth Multi-Axis Optimization of Vision Transformers for Semiconductor IC Packaging
Authors
-
#11 Tamper-Sensitive Key-Controlled Adaptive Multi-Bit Symbol-Mask Data Hiding for Authenticated Secret Image Recovery
Authors
-
#186 Base-Consistent Diffusion Refinement with Space-Varying Blur Operators for Cross-Domain Motion Deblurring
Authors
Day 4 – Wednesday, 16 December 2026
VSPC Rising Star 1: From Prototype to Impact: Shaping the Future of Live Streaming Powered by Video Complexity Analysis
VSPC Rising Star 2: Learning-Based Data Compression: From Visual Signals to Broader Modalities
Oral Session 11: S11 Coding for Machines and Task-Aware Compression
-
#105 Single-Bitstream Decoupling for Tiered Human and Machine Consumption via Tier-Controlled Coding
Authors
-
#207 Generalizable Variable-Rate Adaptation for Image Coding for Machines
Authors
-
#139 Learning-Based Scalable Image Feature Coding for Machines
Authors
-
#194 Inter-Frame Predictive Contour Coding for Semantic Map Compression
Authors
-
#123 Task-Aware Bitrate Thresholds for Codec-Robust Ultrasound Segmentation
Authors
Oral Session 12: S12 Best Paper Finalist Session
-
#104 NICER: Neural Image Codecs with Randomness for Perceptual Quality Adaptation
Authors
-
#213 Neural Image Compression with Internal-External Prior Fusion and Alignment
Authors
-
#163 Event-Based Optical Flow Constraint via Time-Sliced Plane Fitting
Authors
-
#112 Towards Fine-Grained Scalable Video Compression
Authors
-
#162 NegDrive: Negative Reinforcement to Enhance Reasoning Safety of Vision-Language-Action Models for Autonomous Driving
Authors
Oral Session 13: S13 Vision for Health, Sensing and Privacy
-
#156 OT-BLS: Optimal-Transport-based Backbone Layer Selection for Frozen DINOv3 in Cross-Domain Few-Shot Segmentation
Authors
-
#45 StainPMS: Self-Bootstrapped Prompt-Mask Supervision for Nuclei Instance Segmentation
Authors
-
#42 Decoupled Joint Optimization of Sampling Patterns and Diffusion Models for Accelerated MRI
Authors
-
#191 Directional Navigability Estimation from Ultra-Low-Resolution Multi-View Thermal Sensing
Authors
-
#201 De-Identifying Facial Dataset for Privacy-Preserving Emotion Recognition
Authors
Oral Session 14 (Special Session): S14 SS: Advances in Next-Generation Video Coding
-
#146 An Efficient FPGA Implementation of Intra-Pattern Copy Search for Subband Image Coding
Authors
-
#148 Accelerating Merge with Motion Vector Difference via Filter Difference Analysis for VVenC
Authors
-
#150 Decoder-Guided Lossy Contour Coding Via Anchor Refinement
Authors
-
#172 Vectorization of Non-Angular Intra Prediction for VVC
Authors
-
#137 Arbitrary-Scale Reference Picture Resampling for Versatile Video Coding
Authors
Oral Session 15: S15 Image Compression II
-
#97 Lossless Recompression of Similar JPEG Images with Random Access
Authors
-
#32 EL2IC: Efficient Learned Lossless Image Compression via Network Search, Distillation, and Quantization
Authors
-
#48 Image Tokenizer for Image Compression: A Benchmark and Analysis
Authors
-
#196 Zonal Overfitted Coding for 360° Images
Authors
-
#136 EdgeDiffSR: Edge Map-Assisted One-Step Diffusion for Compressed Image Super-Resolution
Authors
Oral Session 16 (Special Session): S16 SS: Advances in Imaging, Perception, and Reasoning for High-Dimensional Visual Data
-
#179 ENIQA: Evaluating Perceptual Distortions for Robust Embodied Visual Navigation
Authors
-
#116 The Influence of Image Editing on Visual Attention
Authors
-
#70 UNIMASKRC-DPCC: A Unified Mask Residual Coding Framework for End-to-End Learned Dynamic Point Cloud Compression
Authors
-
#170 Geometry-Aware Cross-Exposure Detail Recovery for Light Field Exposure Restoration
Authors
-
#226 Spatial Resampling of V-PCC Maps for Improved Low-Bitrate Point Cloud Compression
Authors
Poster Session 3: P3 Visual Understanding, Multimodal and Medical
-
#44 FedYOGA: Federated YOLO-based Group-wise Aggregation for Cross-Domain Object Detection
Authors
-
#85 Seeing Beyond the Frame: Inferring Out-of-View Objects from Scene Context
Authors
-
#90 Learning Geometric Awareness for Facial Landmark Detection via Structural Knowledge Distillation
Authors
-
#113 Spatio-Temporal Player-Ball Graphs for Soccer Pass Direction Prediction
Authors
-
#125 Spatial-Temporal Mixture-of-Experts-Guided Modality Calibration for Continual Egocentric Activity Recognition
Authors
-
#140 A Global Enhancement Layer-Based Framework for Visual Speech Recognition
Authors
-
#177 Script-Aware CNN-FPN Transformer for Offline Handwritten Urdu Text Recognition
Authors
-
#199 A Robust Real-Time Object Tracking with Global Motion Compensation and Internal Active Search
Authors
-
#236 Spatially-Aware Class-Agnostic Object Counting
Authors
-
#38 PriceSeer: Evaluating Large Language Models in Real-Time Stock Prediction
Authors
-
#64 RoboPhoto-VLA: Robotic Photography System based on Vision-Language-Action Model
Authors
-
#89 FLINT: Fine-Tuned LLMs for Instructed Trajectory Generation in Crowd Simulation
Authors
-
#182 Towards Reliable Food Segmentation for Nutritional Monitoring
Authors
-
#188 MASP-UNet: Acquisition-Aware Lightweight Segmentation of Renal Structures in Ultrasound
Authors
-
#102 CBSF-Net: Cross-Modal Bidirectional State Space Fusion for Guided Depth Super-Resolution
Authors