Human Preference-Aligned Concept Customization Benchmark via Decomposed Evaluation

Evaluating concept customization is challenging, as it requires a comprehensive assessment of fidelity to generative prompts and concept images. Moreover, evaluating multiple concepts is considerably more difficult than evaluating a single concept, as it demands detailed assessment not only for each individual concept but also for the interactions among concepts. While humans can intuitively assess generated images, existing metrics often provide either overly narrow or overly generalized evaluations, resulting in misalignment with human preference. To address this, we propose Decomposed GPT Score (D-GPTScore), a novel human-aligned evaluation method that decomposes evaluation criteria into finer aspects and incorporates aspect-wise assessments using Multimodal Large Language Model (MLLM). Additionally, we release Human Preference-Aligned Concept Customization Benchmark (CC-AlignBench), a benchmark dataset containing both single- and multi-concept tasks, enabling stage-wise evaluation across a wide difficulty range -- from individual actions to multi-person interactions. Our method significantly outperforms existing approaches on this benchmark, exhibiting higher correlation with human preferences. This work establishes a new standard for evaluating concept customization and highlights key challenges for future research. The benchmark and associated materials are available at https://github.com/ReinaIshikawa/D-GPTScore.

SoccerNet 2025 Challenges Results

The SoccerNet 2025 Challenges mark the fifth annual edition of the SoccerNet open benchmarking effort, dedicated to advancing computer vision research in football video understanding. This year's challenges span four vision-based tasks: (1) Team Ball Action Spotting, focused on detecting ball-related actions in football broadcasts and assigning actions to teams; (2) Monocular Depth Estimation, targeting the recovery of scene geometry from single-camera broadcast clips through relative depth estimation for each pixel; (3) Multi-View Foul Recognition, requiring the analysis of multiple synchronized camera views to classify fouls and their severity; and (4) Game State Reconstruction, aimed at localizing and identifying all players from a broadcast video to reconstruct the game state on a 2D top-view of the field. Across all tasks, participants were provided with large-scale annotated datasets, unified evaluation protocols, and strong baselines as starting points. This report presents the results of each challenge, highlights the top-performing solutions, and provides insights into the progress made by the community. The SoccerNet Challenges continue to serve as a driving force for reproducible, open research at the intersection of computer vision, artificial intelligence, and sports. Detailed information about the tasks, challenges, and leaderboards can be found at https://www.soccer-net.org, with baselines and development kits available at https://github.com/SoccerNet.

User-in-the-Loop View Sampling with Error Peaking Visualization

Augmented reality (AR) provides ways to visualize missing view samples for novel view synthesis. Existing approaches present 3D annotations for new view samples and task users with taking images by aligning the AR display. This data collection task is known to be mentally demanding and limits capture areas to pre-defined small areas due to the ideal but restrictive underlying sampling theory. To free users from 3D annotations and limited scene exploration, we propose using locally reconstructed light fields and visualizing errors to be removed by inserting new views. Our results show that the error-peaking visualization is less invasive, reduces disappointment in final results, and is satisfactory with fewer view samples in our mobile view synthesis system. We also show that our approach can contribute to recent radiance field reconstruction for larger scenes, such as 3D Gaussian splatting.

The Invisible EgoHand: 3D Hand Forecasting through EgoBody Pose Estimation

Forecasting hand motion and pose from an egocentric perspective is essential for understanding human intention. However, existing methods focus solely on predicting positions without considering articulation, and only when the hands are visible in the field of view. This limitation overlooks the fact that approximate hand positions can still be inferred even when they are outside the camera's view. In this paper, we propose a method to forecast the 3D trajectories and poses of both hands from an egocentric video, both in and out of the field of view. We propose a diffusion-based transformer architecture for Egocentric Hand Forecasting, EgoH4, which takes as input the observation sequence and camera poses, then predicts future 3D motion and poses for both hands of the camera wearer. We leverage full-body pose information, allowing other joints to provide constraints on hand motion. We denoise the hand and body joints along with a visibility predictor for hand joints and a 3D-to-2D reprojection loss that minimizes the error when hands are in-view. We evaluate EgoH4 on the Ego-Exo4D dataset, combining subsets with body and hand annotations. We train on 156K sequences and evaluate on 34K sequences, respectively. EgoH4 improves the performance by 3.4cm and 5.1cm over the baseline in terms of ADE for hand trajectory forecasting and MPJPE for hand pose forecasting. Project page: https://masashi-hatano.github.io/EgoH4/

EgoSurgery-HTS: A Dataset for Egocentric Hand-Tool Segmentation in Open Surgery Videos

Egocentric open-surgery videos capture rich, fine-grained details essential for accurately modeling surgical procedures and human behavior in the operating room. A detailed, pixel-level understanding of hands and surgical tools is crucial for interpreting a surgeon's actions and intentions. We introduce EgoSurgery-HTS, a new dataset with pixel-wise annotations and a benchmark suite for segmenting surgical tools, hands, and interacting tools in egocentric open-surgery videos. Specifically, we provide a labeled dataset for (1) tool instance segmentation of 14 distinct surgical tools, (2) hand instance segmentation, and (3) hand-tool segmentation to label hands and the tools they manipulate. Using EgoSurgery-HTS, we conduct extensive evaluations of state-of-the-art segmentation methods and demonstrate significant improvements in the accuracy of hand and hand-tool segmentation in egocentric open-surgery videos compared to existing datasets. The dataset will be released at https://github.com/Fujiry0/EgoSurgery.

High-Quality Virtual Single-Viewpoint Surgical Video: Geometric Autocalibration of Multiple Cameras in Surgical Lights

Occlusion-free video generation is challenging due to surgeons' obstructions in the camera field of view. Prior work has addressed this issue by installing multiple cameras on a surgical light, hoping some cameras will observe the surgical field with less occlusion. However, this special camera setup poses a new imaging challenge since camera configurations can change every time surgeons move the light, and manual image alignment is required. This paper proposes an algorithm to automate this alignment task. The proposed method detects frames where the lighting system moves, realigns them, and selects the camera with the least occlusion. This algorithm results in a stabilized video with less occlusion. Quantitative results show that our method outperforms conventional approaches. A user study involving medical doctors also confirmed the superiority of our method.

Dense Depth from Event Focal Stack

We propose a method for dense depth estimation from an event stream generated when sweeping the focal plane of the driving lens attached to an event camera. In this method, a depth map is inferred from an ``event focal stack'' composed of the event stream using a convolutional neural network trained with synthesized event focal stacks. The synthesized event stream is created from a focal stack generated by Blender for any arbitrary 3D scene. This allows for training on scenes with diverse structures. Additionally, we explored methods to eliminate the domain gap between real event streams and synthetic event streams. Our method demonstrates superior performance over a depth-from-defocus method in the image domain on synthetic and real datasets.

RealTraj: Towards Real-World Pedestrian Trajectory Forecasting

This paper jointly addresses three key limitations in conventional pedestrian trajectory forecasting: pedestrian perception errors, real-world data collection costs, and person ID annotation costs. We propose a novel framework, RealTraj, that enhances the real-world applicability of trajectory forecasting. Our approach includes two training phases--self-supervised pretraining on synthetic data and weakly-supervised fine-tuning with limited real-world data--to minimize data collection efforts. To improve robustness to real-world errors, we focus on both model design and training objectives. Specifically, we present Det2TrajFormer, a trajectory forecasting model that remains invariant in tracking noise by using past detections as inputs. Additionally, we pretrain the model using multiple pretext tasks, which enhance robustness and improve forecasting performance based solely on detection data. Unlike previous trajectory forecasting methods, our approach fine-tunes the model using only ground-truth detections, significantly reducing the need for costly person ID annotations. In the experiments, we comprehensively verify the effectiveness of the proposed method against the limitations, and the method outperforms state-of-the-art trajectory forecasting methods on multiple datasets.

Visuo-Tactile Zero-Shot Object Recognition with Vision-Language Model

Tactile perception is vital, especially when distinguishing visually similar objects. We propose an approach to incorporate tactile data into a Vision-Language Model (VLM) for visuo-tactile zero-shot object recognition. Our approach leverages the zero-shot capability of VLMs to infer tactile properties from the names of tactilely similar objects. The proposed method translates tactile data into a textual description solely by annotating object names for each tactile sequence during training, making it adaptable to various contexts with low training costs. The proposed method was evaluated on the FoodReplica and Cube datasets, demonstrating its effectiveness in recognizing objects that are difficult to distinguish by vision alone.

CrowdMAC: Masked Crowd Density Completion for Robust Crowd Density Forecasting

A crowd density forecasting task aims to predict how the crowd density map will change in the future from observed past crowd density maps. However, the past crowd density maps are often incomplete due to the miss-detection of pedestrians, and it is crucial to develop a robust crowd density forecasting model against the miss-detection. This paper presents a MAsked crowd density Completion framework for crowd density forecasting (CrowdMAC), which is simultaneously trained to forecast future crowd density maps from partially masked past crowd density maps (i.e., forecasting maps from past maps with miss-detection) while reconstructing the masked observation maps (i.e., imputing past maps with miss-detection). Additionally, we propose Temporal-Density-aware Masking (TDM), which non-uniformly masks tokens in the observed crowd density map, considering the sparsity of the crowd density maps and the informativeness of the subsequent frames for the forecasting task. Moreover, we introduce multi-task masking to enhance training efficiency. In the experiments, CrowdMAC achieves state-of-the-art performance on seven large-scale datasets, including SDD, ETH-UCY, inD, JRDB, VSCrowd, FDST, and croHD. We also demonstrate the robustness of the proposed method against both synthetic and realistic miss-detections.