Kyoung Mu Lee

JoonKyu Park, Yeonguk Oh, Gyeongsik Moon et al.

Hands are often severely occluded by objects, which makes 3D hand mesh estimation challenging. Previous works often have disregarded information at occluded regions. However, we argue that occluded regions have strong correlations with hands so that they can provide highly beneficial information for complete 3D hand mesh estimation. Thus, in this work, we propose a novel 3D hand mesh estimation network HandOccNet, that can fully exploits the information at occluded regions as a secondary means to enhance image features and make it much richer. To this end, we design two successive Transformer-based modules, called feature injecting transformer (FIT) and self- enhancing transformer (SET). FIT injects hand information into occluded region by considering their correlation. SET refines the output of FIT by using a self-attention mechanism. By injecting the hand information to the occluded region, our HandOccNet reaches the state-of-the-art performance on 3D hand mesh benchmarks that contain challenging hand-object occlusions. The codes are available in: https://github.com/namepllet/HandOccNet.

Gyeongsik Moon, Hyeongjin Nam, Takaaki Shiratori et al.

Although much progress has been made in 3D clothed human reconstruction, most of the existing methods fail to produce robust results from in-the-wild images, which contain diverse human poses and appearances. This is mainly due to the large domain gap between training datasets and in-the-wild datasets. The training datasets are usually synthetic ones, which contain rendered images from GT 3D scans. However, such datasets contain simple human poses and less natural image appearances compared to those of real in-the-wild datasets, which makes generalization of it to in-the-wild images extremely challenging. To resolve this issue, in this work, we propose ClothWild, a 3D clothed human reconstruction framework that firstly addresses the robustness on in-thewild images. First, for the robustness to the domain gap, we propose a weakly supervised pipeline that is trainable with 2D supervision targets of in-the-wild datasets. Second, we design a DensePose-based loss function to reduce ambiguities of the weak supervision. Extensive empirical tests on several public in-the-wild datasets demonstrate that our proposed ClothWild produces much more accurate and robust results than the state-of-the-art methods. The codes are available in here: https://github.com/hygenie1228/ClothWild_RELEASE.

JoonKyu Park, Daniel Sungho Jung, Gyeongsik Moon et al.

Understanding how two hands interact with each other is a key component of accurate 3D interacting hand mesh recovery. However, recent Transformer-based methods struggle to learn the interaction between two hands as they directly utilize two hand features as input tokens, which results in distant token problem. The distant token problem represents that input tokens are in heterogeneous spaces, leading Transformer to fail in capturing correlation between input tokens. Previous Transformer-based methods suffer from the problem especially when poses of two hands are very different as they project features from a backbone to separate left and right hand-dedicated features. We present EANet, extract-and-adaptation network, with EABlock, the main component of our network. Rather than directly utilizing two hand features as input tokens, our EABlock utilizes two complementary types of novel tokens, SimToken and JoinToken, as input tokens. Our two novel tokens are from a combination of separated two hand features; hence, it is much more robust to the distant token problem. Using the two type of tokens, our EABlock effectively extracts interaction feature and adapts it to each hand. The proposed EANet achieves the state-of-the-art performance on 3D interacting hands benchmarks. The codes are available at https://github.com/jkpark0825/EANet.

Reyhaneh Neshatavar, Mohsen Yavartanoo, Sanghyun Son et al.

Recently, significant progress has been made on image denoising with strong supervision from large-scale datasets. However, obtaining well-aligned noisy-clean training image pairs for each specific scenario is complicated and costly in practice. Consequently, applying a conventional supervised denoising network on in-the-wild noisy inputs is not straightforward. Although several studies have challenged this problem without strong supervision, they rely on less practical assumptions and cannot be applied to practical situations directly. To address the aforementioned challenges, we propose a novel and powerful self-supervised denoising method called CVF-SID based on a Cyclic multi-Variate Function (CVF) module and a self-supervised image disentangling (SID) framework. The CVF module can output multiple decomposed variables of the input and take a combination of the outputs back as an input in a cyclic manner. Our CVF-SID can disentangle a clean image and noise maps from the input by leveraging various self-supervised loss terms. Unlike several methods that only consider the signal-independent noise models, we also deal with signal-dependent noise components for real-world applications. Furthermore, we do not rely on any prior assumptions about the underlying noise distribution, making CVF-SID more generalizable toward realistic noise. Extensive experiments on real-world datasets show that CVF-SID achieves state-of-the-art self-supervised image denoising performance and is comparable to other existing approaches. The code is publicly available from https://github.com/Reyhanehne/CVF-SID_PyTorch .

Taeryung Lee, Gyeongsik Moon, Kyoung Mu Lee

We tackle the problem of generating long-term 3D human motion from multiple action labels. Two main previous approaches, such as action- and motion-conditioned methods, have limitations to solve this problem. The action-conditioned methods generate a sequence of motion from a single action. Hence, it cannot generate long-term motions composed of multiple actions and transitions between actions. Meanwhile, the motion-conditioned methods generate future motions from initial motion. The generated future motions only depend on the past, so they are not controllable by the user's desired actions. We present MultiAct, the first framework to generate long-term 3D human motion from multiple action labels. MultiAct takes account of both action and motion conditions with a unified recurrent generation system. It repetitively takes the previous motion and action label; then, it generates a smooth transition and the motion of the given action. As a result, MultiAct produces realistic long-term motion controlled by the given sequence of multiple action labels. Codes are available here at https://github.com/TaeryungLee/MultiAct_RELEASE.

Cheeun Hong, Sungyong Baik, Heewon Kim et al.

Despite breakthrough advances in image super-resolution (SR) with convolutional neural networks (CNNs), SR has yet to enjoy ubiquitous applications due to the high computational complexity of SR networks. Quantization is one of the promising approaches to solve this problem. However, existing methods fail to quantize SR models with a bit-width lower than 8 bits, suffering from severe accuracy loss due to fixed bit-width quantization applied everywhere. In this work, to achieve high average bit-reduction with less accuracy loss, we propose a novel Content-Aware Dynamic Quantization (CADyQ) method for SR networks that allocates optimal bits to local regions and layers adaptively based on the local contents of an input image. To this end, a trainable bit selector module is introduced to determine the proper bit-width and quantization level for each layer and a given local image patch. This module is governed by the quantization sensitivity that is estimated by using both the average magnitude of image gradient of the patch and the standard deviation of the input feature of the layer. The proposed quantization pipeline has been tested on various SR networks and evaluated on several standard benchmarks extensively. Significant reduction in computational complexity and the elevated restoration accuracy clearly demonstrate the effectiveness of the proposed CADyQ framework for SR. Codes are available at https://github.com/Cheeun/CADyQ.

Taehoon Kim, Pyunghwan Ahn, Sangyun Kim et al. · nvidia, utoronto

In this report, we introduce NICE (New frontiers for zero-shot Image Captioning Evaluation) project and share the results and outcomes of 2023 challenge. This project is designed to challenge the computer vision community to develop robust image captioning models that advance the state-of-the-art both in terms of accuracy and fairness. Through the challenge, the image captioning models were tested using a new evaluation dataset that includes a large variety of visual concepts from many domains. There was no specific training data provided for the challenge, and therefore the challenge entries were required to adapt to new types of image descriptions that had not been seen during training. This report includes information on the newly proposed NICE dataset, evaluation methods, challenge results, and technical details of top-ranking entries. We expect that the outcomes of the challenge will contribute to the improvement of AI models on various vision-language tasks.

Hyeongjin Nam, Daniel Sungho Jung, Yeonguk Oh et al.

Despite recent advances in 3D human mesh reconstruction, domain gap between training and test data is still a major challenge. Several prior works tackle the domain gap problem via test-time adaptation that fine-tunes a network relying on 2D evidence (e.g., 2D human keypoints) from test images. However, the high reliance on 2D evidence during adaptation causes two major issues. First, 2D evidence induces depth ambiguity, preventing the learning of accurate 3D human geometry. Second, 2D evidence is noisy or partially non-existent during test time, and such imperfect 2D evidence leads to erroneous adaptation. To overcome the above issues, we introduce CycleAdapt, which cyclically adapts two networks: a human mesh reconstruction network (HMRNet) and a human motion denoising network (MDNet), given a test video. In our framework, to alleviate high reliance on 2D evidence, we fully supervise HMRNet with generated 3D supervision targets by MDNet. Our cyclic adaptation scheme progressively elaborates the 3D supervision targets, which compensate for imperfect 2D evidence. As a result, our CycleAdapt achieves state-of-the-art performance compared to previous test-time adaptation methods. The codes are available at https://github.com/hygenie1228/CycleAdapt_RELEASE.

Junghun Oh, Heewon Kim, Seungjun Nah et al.

Image restoration tasks have witnessed great performance improvement in recent years by developing large deep models. Despite the outstanding performance, the heavy computation demanded by the deep models has restricted the application of image restoration. To lift the restriction, it is required to reduce the size of the networks while maintaining accuracy. Recently, N:M structured pruning has appeared as one of the effective and practical pruning approaches for making the model efficient with the accuracy constraint. However, it fails to account for different computational complexities and performance requirements for different layers of an image restoration network. To further optimize the trade-off between the efficiency and the restoration accuracy, we propose a novel pruning method that determines the pruning ratio for N:M structured sparsity at each layer. Extensive experimental results on super-resolution and deblurring tasks demonstrate the efficacy of our method which outperforms previous pruning methods significantly. PyTorch implementation for the proposed methods is available at https://github.com/JungHunOh/SLS_CVPR2022.

Sangmin Hong, Mohsen Yavartanoo, Reyhaneh Neshatavar et al.

Point cloud completion addresses filling in the missing parts of a partial point cloud obtained from depth sensors and generating a complete point cloud. Although there has been steep progress in the supervised methods on the synthetic point cloud completion task, it is hardly applicable in real-world scenarios due to the domain gap between the synthetic and real-world datasets or the requirement of prior information. To overcome these limitations, we propose a novel self-supervised framework ACL-SPC for point cloud completion to train and test on the same data. ACL-SPC takes a single partial input and attempts to output the complete point cloud using an adaptive closed-loop (ACL) system that enforces the output same for the variation of an input. We evaluate our proposed ACL-SPC on various datasets to prove that it can successfully learn to complete a partial point cloud as the first self-supervised scheme. Results show that our method is comparable with unsupervised methods and achieves superior performance on the real-world dataset compared to the supervised methods trained on the synthetic dataset. Extensive experiments justify the necessity of self-supervised learning and the effectiveness of our proposed method for the real-world point cloud completion task. The code is publicly available from https://github.com/Sangminhong/ACL-SPC_PyTorch

Yeonguk Oh, JoonKyu Park, Jaeha Kim et al.

Hands, one of the most dynamic parts of our body, suffer from blur due to their active movements. However, previous 3D hand mesh recovery methods have mainly focused on sharp hand images rather than considering blur due to the absence of datasets providing blurry hand images. We first present a novel dataset BlurHand, which contains blurry hand images with 3D groundtruths. The BlurHand is constructed by synthesizing motion blur from sequential sharp hand images, imitating realistic and natural motion blurs. In addition to the new dataset, we propose BlurHandNet, a baseline network for accurate 3D hand mesh recovery from a blurry hand image. Our BlurHandNet unfolds a blurry input image to a 3D hand mesh sequence to utilize temporal information in the blurry input image, while previous works output a static single hand mesh. We demonstrate the usefulness of BlurHand for the 3D hand mesh recovery from blurry images in our experiments. The proposed BlurHandNet produces much more robust results on blurry images while generalizing well to in-the-wild images. The training codes and BlurHand dataset are available at https://github.com/JaehaKim97/BlurHand_RELEASE.

Dongwoo Lee, Jeongtaek Oh, Jaesung Rim et al.

We present ExBluRF, a novel view synthesis method for extreme motion blurred images based on efficient radiance fields optimization. Our approach consists of two main components: 6-DOF camera trajectory-based motion blur formulation and voxel-based radiance fields. From extremely blurred images, we optimize the sharp radiance fields by jointly estimating the camera trajectories that generate the blurry images. In training, multiple rays along the camera trajectory are accumulated to reconstruct single blurry color, which is equivalent to the physical motion blur operation. We minimize the photo-consistency loss on blurred image space and obtain the sharp radiance fields with camera trajectories that explain the blur of all images. The joint optimization on the blurred image space demands painfully increasing computation and resources proportional to the blur size. Our method solves this problem by replacing the MLP-based framework to low-dimensional 6-DOF camera poses and voxel-based radiance fields. Compared with the existing works, our approach restores much sharper 3D scenes from challenging motion blurred views with the order of 10 times less training time and GPU memory consumption.

Seung Yeon Shin, Soochahn Lee, Kyoung Jin Noh et al.

We present a method to extract coronary vessels from fluoroscopic x-ray sequences. Given the vessel structure for the source frame, vessel correspondence candidates in the subsequent frame are generated by a novel hierarchical search scheme to overcome the aperture problem. Optimal correspondences are determined within a Markov random field optimization framework. Post-processing is performed to extract vessel branches newly visible due to the inflow of contrast agent. Quantitative and qualitative evaluation conducted on a dataset of 18 sequences demonstrates the effectiveness of the proposed method.

Wooseok Lee, Sanghyun Son, Kyoung Mu Lee

Blind-spot network (BSN) and its variants have made significant advances in self-supervised denoising. Nevertheless, they are still bound to synthetic noisy inputs due to less practical assumptions like pixel-wise independent noise. Hence, it is challenging to deal with spatially correlated real-world noise using self-supervised BSN. Recently, pixel-shuffle downsampling (PD) has been proposed to remove the spatial correlation of real-world noise. However, it is not trivial to integrate PD and BSN directly, which prevents the fully self-supervised denoising model on real-world images. We propose an Asymmetric PD (AP) to address this issue, which introduces different PD stride factors for training and inference. We systematically demonstrate that the proposed AP can resolve inherent trade-offs caused by specific PD stride factors and make BSN applicable to practical scenarios. To this end, we develop AP-BSN, a state-of-the-art self-supervised denoising method for real-world sRGB images. We further propose random-replacing refinement, which significantly improves the performance of our AP-BSN without any additional parameters. Extensive studies demonstrate that our method outperforms the other self-supervised and even unpaired denoising methods by a large margin, without using any additional knowledge, e.g., noise level, regarding the underlying unknown noise.

Hongsuk Choi, Gyeongsik Moon, Matthieu Armando et al.

Existing neural human rendering methods struggle with a single image input due to the lack of information in invisible areas and the depth ambiguity of pixels in visible areas. In this regard, we propose Monocular Neural Human Renderer (MonoNHR), a novel approach that renders robust free-viewpoint images of an arbitrary human given only a single image. MonoNHR is the first method that (i) renders human subjects never seen during training in a monocular setup, and (ii) is trained in a weakly-supervised manner without geometry supervision. First, we propose to disentangle 3D geometry and texture features and to condition the texture inference on the 3D geometry features. Second, we introduce a Mesh Inpainter module that inpaints the occluded parts exploiting human structural priors such as symmetry. Experiments on ZJU-MoCap, AIST, and HUMBI datasets show that our approach significantly outperforms the recent methods adapted to the monocular case.

Jaeyoung Chung, Kanggeon Lee, Sungyong Baik et al.

Hinged on the representation power of neural networks, neural radiance fields (NeRF) have recently emerged as one of the promising and widely applicable methods for 3D object and scene representation. However, NeRF faces challenges in practical applications, such as large-scale scenes and edge devices with a limited amount of memory, where data needs to be processed sequentially. Under such incremental learning scenarios, neural networks are known to suffer catastrophic forgetting: easily forgetting previously seen data after training with new data. We observe that previous incremental learning algorithms are limited by either low performance or memory scalability issues. As such, we develop a Memory-Efficient Incremental Learning algorithm for NeRF (MEIL-NeRF). MEIL-NeRF takes inspiration from NeRF itself in that a neural network can serve as a memory that provides the pixel RGB values, given rays as queries. Upon the motivation, our framework learns which rays to query NeRF to extract previous pixel values. The extracted pixel values are then used to train NeRF in a self-distillation manner to prevent catastrophic forgetting. As a result, MEIL-NeRF demonstrates constant memory consumption and competitive performance.

Daniel Sungho Jung, Kyoung Mu Lee

Dense hand contact estimation requires both high-level semantic understanding and fine-grained geometric reasoning of human interaction to accurately localize contact regions. Recently, multi-modal large language models (MLLMs) have demonstrated strong capabilities in understanding visual semantics, enabled by vision-language priors learned from large-scale data. However, leveraging MLLMs for dense hand contact estimation remains underexplored. There are two major challenges in applying MLLMs to dense hand contact estimation. First, encoding explicit 3D hand geometry is difficult, as MLLMs primarily operate on vision and language modalities. Second, capturing fine-grained vertex-level contact remains challenging, as MLLMs tend to focus on high-level semantics rather than detailed geometric reasoning. To address these challenges, we propose ContactPrompt, a training-free and zero-shot approach for dense hand contact estimation using MLLMs. To effectively encode 3D hand geometry, we introduce a detailed hand-part segmentation and a part-wise vertex-grid representation that provides structured, localized geometric information. To enable accurate and efficient dense contact prediction, we develop a multi-stage structured contact reasoning with part conditioning, progressively bridging global semantics and fine-grained geometry. Therefore, our method effectively leverages the reasoning capabilities of MLLMs while enabling precise dense hand contact estimation. Surprisingly, the proposed approach outperforms previous supervised methods trained on large-scale dense contact datasets without requiring any training. The codes will be released.

Taeryung Lee, Yeonguk Oh, Kyoung Mu Lee

In this paper, we propose P3D, the human part-wise motion context learning framework for sign language recognition. Our main contributions lie in two dimensions: learning the part-wise motion context and employing the pose ensemble to utilize 2D and 3D pose jointly. First, our empirical observation implies that part-wise context encoding benefits the performance of sign language recognition. While previous methods of sign language recognition learned motion context from the sequence of the entire pose, we argue that such methods cannot exploit part-specific motion context. In order to utilize part-wise motion context, we propose the alternating combination of a part-wise encoding Transformer (PET) and a whole-body encoding Transformer (WET). PET encodes the motion contexts from a part sequence, while WET merges them into a unified context. By learning part-wise motion context, our P3D achieves superior performance on WLASL compared to previous state-of-the-art methods. Second, our framework is the first to ensemble 2D and 3D poses for sign language recognition. Since the 3D pose holds rich motion context and depth information to distinguish the words, our P3D outperformed the previous state-of-the-art methods employing a pose ensemble.

Jaeyoung Chung, Suyoung Lee, Hyeongjin Nam et al.

With the widespread usage of VR devices and contents, demands for 3D scene generation techniques become more popular. Existing 3D scene generation models, however, limit the target scene to specific domain, primarily due to their training strategies using 3D scan dataset that is far from the real-world. To address such limitation, we propose LucidDreamer, a domain-free scene generation pipeline by fully leveraging the power of existing large-scale diffusion-based generative model. Our LucidDreamer has two alternate steps: Dreaming and Alignment. First, to generate multi-view consistent images from inputs, we set the point cloud as a geometrical guideline for each image generation. Specifically, we project a portion of point cloud to the desired view and provide the projection as a guidance for inpainting using the generative model. The inpainted images are lifted to 3D space with estimated depth maps, composing a new points. Second, to aggregate the new points into the 3D scene, we propose an aligning algorithm which harmoniously integrates the portions of newly generated 3D scenes. The finally obtained 3D scene serves as initial points for optimizing Gaussian splats. LucidDreamer produces Gaussian splats that are highly-detailed compared to the previous 3D scene generation methods, with no constraint on domain of the target scene. Project page: https://luciddreamer-cvlab.github.io/

Reyhaneh Neshatavar, Mohsen Yavartanoo, Sanghyun Son et al.

Single image super-resolution (SISR) is a challenging ill-posed problem that aims to up-sample a given low-resolution (LR) image to a high-resolution (HR) counterpart. Due to the difficulty in obtaining real LR-HR training pairs, recent approaches are trained on simulated LR images degraded by simplified down-sampling operators, e.g., bicubic. Such an approach can be problematic in practice because of the large gap between the synthesized and real-world LR images. To alleviate the issue, we propose a novel Invertible scale-Conditional Function (ICF), which can scale an input image and then restore the original input with different scale conditions. By leveraging the proposed ICF, we construct a novel self-supervised SISR framework (ICF-SRSR) to handle the real-world SR task without using any paired/unpaired training data. Furthermore, our ICF-SRSR can generate realistic and feasible LR-HR pairs, which can make existing supervised SISR networks more robust. Extensive experiments demonstrate the effectiveness of the proposed method in handling SISR in a fully self-supervised manner. Our ICF-SRSR demonstrates superior performance compared to the existing methods trained on synthetic paired images in real-world scenarios and exhibits comparable performance compared to state-of-the-art supervised/unsupervised methods on public benchmark datasets.

Hongsuk Choi, Hyeongjin Nam, Taeryung Lee et al.

Recently, a few self-supervised representation learning (SSL) methods have outperformed the ImageNet classification pre-training for vision tasks such as object detection. However, its effects on 3D human body pose and shape estimation (3DHPSE) are open to question, whose target is fixed to a unique class, the human, and has an inherent task gap with SSL. We empirically study and analyze the effects of SSL and further compare it with other pre-training alternatives for 3DHPSE. The alternatives are 2D annotation-based pre-training and synthetic data pre-training, which share the motivation of SSL that aims to reduce the labeling cost. They have been widely utilized as a source of weak-supervision or fine-tuning, but have not been remarked as a pre-training source. SSL methods underperform the conventional ImageNet classification pre-training on multiple 3DHPSE benchmarks by 7.7% on average. In contrast, despite a much less amount of pre-training data, the 2D annotation-based pre-training improves accuracy on all benchmarks and shows faster convergence during fine-tuning. Our observations challenge the naive application of the current SSL pre-training to 3DHPSE and relight the value of other data types in the pre-training aspect.

Jaeyoung Chung, Jeongtaek Oh, Kyoung Mu Lee

In this paper, we present a method to optimize Gaussian splatting with a limited number of images while avoiding overfitting. Representing a 3D scene by combining numerous Gaussian splats has yielded outstanding visual quality. However, it tends to overfit the training views when only a small number of images are available. To address this issue, we introduce a dense depth map as a geometry guide to mitigate overfitting. We obtained the depth map using a pre-trained monocular depth estimation model and aligning the scale and offset using sparse COLMAP feature points. The adjusted depth aids in the color-based optimization of 3D Gaussian splatting, mitigating floating artifacts, and ensuring adherence to geometric constraints. We verify the proposed method on the NeRF-LLFF dataset with varying numbers of few images. Our approach demonstrates robust geometry compared to the original method that relies solely on images. Project page: robot0321.github.io/DepthRegGS

Joonkyu Park, Seungjun Nah, Kyoung Mu Lee

State-of-the-art video deblurring methods often adopt recurrent neural networks to model the temporal dependency between the frames. While the hidden states play key role in delivering information to the next frame, abrupt motion blur tend to weaken the relevance in the neighbor frames. In this paper, we propose recurrence-in-recurrence network architecture to cope with the limitations of short-ranged memory. We employ additional recurrent units inside the RNN cell. First, we employ inner-recurrence module (IRM) to manage the long-ranged dependency in a sequence. IRM learns to keep track of the cell memory and provides complementary information to find the deblurred frames. Second, we adopt an attention-based temporal blending strategy to extract the necessary part of the information in the local neighborhood. The adpative temporal blending (ATB) can either attenuate or amplify the features by the spatial attention. Our extensive experimental results and analysis validate the effectiveness of IRM and ATB on various RNN architectures.

Cheeun Hong, Kyoung Mu Lee

Although quantization has emerged as a promising approach to reducing computational complexity across various high-level vision tasks, it inevitably leads to accuracy loss in image super-resolution (SR) networks. This is due to the significantly divergent feature distributions across different channels and input images of the SR networks, which complicates the selection of a fixed quantization range. Existing works address this distribution mismatch problem by dynamically adapting quantization ranges to the varying distributions during test time. However, such a dynamic adaptation incurs additional computational costs during inference. In contrast, we propose a new quantization-aware training scheme that effectively Overcomes the Distribution Mismatch problem in SR networks without the need for dynamic adaptation. Intuitively, this mismatch can be mitigated by regularizing the distance between the feature and a fixed quantization range. However, we observe that such regularization can conflict with the reconstruction loss during training, negatively impacting SR accuracy. Therefore, we opt to regularize the mismatch only when the gradients of the regularization are aligned with those of the reconstruction loss. Additionally, we introduce a layer-wise weight clipping correction scheme to determine a more suitable quantization range for layer-wise weights. Experimental results demonstrate that our framework effectively reduces the distribution mismatch and achieves state-of-the-art performance with minimal computational overhead.

Heewon Kim, Kyoung Mu Lee

Editing flat-looking images into stunning photographs requires skill and time. Automated image enhancement algorithms have attracted increased interest by generating high-quality images without user interaction. However, the quality assessment of a photograph is subjective. Even in tone and color adjustments, a single photograph of auto-enhancement is challenging to fit user preferences which are subtle and even changeable. To address this problem, we present a semiautomatic image enhancement algorithm that can generate high-quality images with multiple styles by controlling a few parameters. We first disentangle photo retouching skills from high-quality images and build an efficient enhancement system for each skill. Specifically, an encoder-decoder framework encodes the retouching skills into latent codes and decodes them into the parameters of image signal processing (ISP) functions. The ISP functions are computationally efficient and consist of only 19 parameters. Despite our approach requiring multiple inferences to obtain the desired result, experimental results present that the proposed method achieves state-of-the-art performances on the benchmark dataset for image quality and model efficiency.

Hyeongjin Nam, Daniel Sungho Jung, Gyeongsik Moon et al.

Human-object contact serves as a strong cue to understand how humans physically interact with objects. Nevertheless, it is not widely explored to utilize human-object contact information for the joint reconstruction of 3D human and object from a single image. In this work, we present a novel joint 3D human-object reconstruction method (CONTHO) that effectively exploits contact information between humans and objects. There are two core designs in our system: 1) 3D-guided contact estimation and 2) contact-based 3D human and object refinement. First, for accurate human-object contact estimation, CONTHO initially reconstructs 3D humans and objects and utilizes them as explicit 3D guidance for contact estimation. Second, to refine the initial reconstructions of 3D human and object, we propose a novel contact-based refinement Transformer that effectively aggregates human features and object features based on the estimated human-object contact. The proposed contact-based refinement prevents the learning of erroneous correlation between human and object, which enables accurate 3D reconstruction. As a result, our CONTHO achieves state-of-the-art performance in both human-object contact estimation and joint reconstruction of 3D human and object. The code is publicly available at https://github.com/dqj5182/CONTHO_RELEASE.

Jaeha Kim, Junghun Oh, Kyoung Mu Lee

In real-world scenarios, image recognition tasks, such as semantic segmentation and object detection, often pose greater challenges due to the lack of information available within low-resolution (LR) content. Image super-resolution (SR) is one of the promising solutions for addressing the challenges. However, due to the ill-posed property of SR, it is challenging for typical SR methods to restore task-relevant high-frequency contents, which may dilute the advantage of utilizing the SR method. Therefore, in this paper, we propose Super-Resolution for Image Recognition (SR4IR) that effectively guides the generation of SR images beneficial to achieving satisfactory image recognition performance when processing LR images. The critical component of our SR4IR is the task-driven perceptual (TDP) loss that enables the SR network to acquire task-specific knowledge from a network tailored for a specific task. Moreover, we propose a cross-quality patch mix and an alternate training framework that significantly enhances the efficacy of the TDP loss by addressing potential problems when employing the TDP loss. Through extensive experiments, we demonstrate that our SR4IR achieves outstanding task performance by generating SR images useful for a specific image recognition task, including semantic segmentation, object detection, and image classification. The implementation code is available at https://github.com/JaehaKim97/SR4IR.

Cheeun Hong, Kyoung Mu Lee

Although image super-resolution (SR) problem has experienced unprecedented restoration accuracy with deep neural networks, it has yet limited versatile applications due to the substantial computational costs. Since different input images for SR face different restoration difficulties, adapting computational costs based on the input image, referred to as adaptive inference, has emerged as a promising solution to compress SR networks. Specifically, adapting the quantization bit-widths has successfully reduced the inference and memory cost without sacrificing the accuracy. However, despite the benefits of the resultant adaptive network, existing works rely on time-intensive quantization-aware training with full access to the original training pairs to learn the appropriate bit allocation policies, which limits its ubiquitous usage. To this end, we introduce the first on-the-fly adaptive quantization framework that accelerates the processing time from hours to seconds. We formulate the bit allocation problem with only two bit mapping modules: one to map the input image to the image-wise bit adaptation factor and one to obtain the layer-wise adaptation factors. These bit mappings are calibrated and fine-tuned using only a small number of calibration images. We achieve competitive performance with the previous adaptive quantization methods, while the processing time is accelerated by x2000. Codes are available at https://github.com/Cheeun/AdaBM.

Suyoung Lee, Jaeyoung Chung, Jaeyoo Huh et al.

Omnidirectional (or 360-degree) images are increasingly being used for 3D applications since they allow the rendering of an entire scene with a single image. Existing works based on neural radiance fields demonstrate successful 3D reconstruction quality on egocentric videos, yet they suffer from long training and rendering times. Recently, 3D Gaussian splatting has gained attention for its fast optimization and real-time rendering. However, directly using a perspective rasterizer to omnidirectional images results in severe distortion due to the different optical properties between two image domains. In this work, we present ODGS, a novel rasterization pipeline for omnidirectional images, with geometric interpretation. For each Gaussian, we define a tangent plane that touches the unit sphere and is perpendicular to the ray headed toward the Gaussian center. We then leverage a perspective camera rasterizer to project the Gaussian onto the corresponding tangent plane. The projected Gaussians are transformed and combined into the omnidirectional image, finalizing the omnidirectional rasterization process. This interpretation reveals the implicit assumptions within the proposed pipeline, which we verify through mathematical proofs. The entire rasterization process is parallelized using CUDA, achieving optimization and rendering speeds 100 times faster than NeRF-based methods. Our comprehensive experiments highlight the superiority of ODGS by delivering the best reconstruction and perceptual quality across various datasets. Additionally, results on roaming datasets demonstrate that ODGS restores fine details effectively, even when reconstructing large 3D scenes. The source code is available on our project page (https://github.com/esw0116/ODGS).

Sangmin Hong, Suyoung Lee, Kyoung Mu Lee

The problem of depth completion involves predicting a dense depth image from a single sparse depth map and an RGB image. Unsupervised depth completion methods have been proposed for various datasets where ground truth depth data is unavailable and supervised methods cannot be applied. However, these models require auxiliary data to estimate depth values, which is far from real scenarios. Monocular depth estimation (MDE) models can produce a plausible relative depth map from a single image, but there is no work to properly combine the sparse depth map with MDE for depth completion; a simple affine transformation to the depth map will yield a high error since MDE are inaccurate at estimating depth difference between objects. We introduce StarryGazer, a domain-agnostic framework that predicts dense depth images from a single sparse depth image and an RGB image without relying on ground-truth depth by leveraging the power of large MDE models. First, we employ a pre-trained MDE model to produce relative depth images. These images are segmented and randomly rescaled to form synthetic pairs for dense pseudo-ground truth and corresponding sparse depths. A refinement network is trained with the synthetic pairs, incorporating the relative depth maps and RGB images to improve the model's accuracy and robustness. StarryGazer shows superior results over existing unsupervised methods and transformed MDE results on various datasets, demonstrating that our framework exploits the power of MDE models while appropriately fixing errors using sparse depth information.

Hongsuk Choi, Gyeongsik Moon, JoonKyu Park et al.

We consider the problem of recovering a single person's 3D human mesh from in-the-wild crowded scenes. While much progress has been in 3D human mesh estimation, existing methods struggle when test input has crowded scenes. The first reason for the failure is a domain gap between training and testing data. A motion capture dataset, which provides accurate 3D labels for training, lacks crowd data and impedes a network from learning crowded scene-robust image features of a target person. The second reason is a feature processing that spatially averages the feature map of a localized bounding box containing multiple people. Averaging the whole feature map makes a target person's feature indistinguishable from others. We present 3DCrowdNet that firstly explicitly targets in-the-wild crowded scenes and estimates a robust 3D human mesh by addressing the above issues. First, we leverage 2D human pose estimation that does not require a motion capture dataset with 3D labels for training and does not suffer from the domain gap. Second, we propose a joint-based regressor that distinguishes a target person's feature from others. Our joint-based regressor preserves the spatial activation of a target by sampling features from the target's joint locations and regresses human model parameters. As a result, 3DCrowdNet learns target-focused features and effectively excludes the irrelevant features of nearby persons. We conduct experiments on various benchmarks and prove the robustness of 3DCrowdNet to the in-the-wild crowded scenes both quantitatively and qualitatively. The code is available at https://github.com/hongsukchoi/3DCrowdNet_RELEASE.

Gyeongsik Moon, Hongsuk Choi, Kyoung Mu Lee

Whole-body 3D human mesh estimation aims to reconstruct the 3D human body, hands, and face simultaneously. Although several methods have been proposed, accurate prediction of 3D hands, which consist of 3D wrist and fingers, still remains challenging due to two reasons. First, the human kinematic chain has not been carefully considered when predicting the 3D wrists. Second, previous works utilize body features for the 3D fingers, where the body feature barely contains finger information. To resolve the limitations, we present Hand4Whole, which has two strong points over previous works. First, we design Pose2Pose, a module that utilizes joint features for 3D joint rotations. Using Pose2Pose, Hand4Whole utilizes hand MCP joint features to predict 3D wrists as MCP joints largely contribute to 3D wrist rotations in the human kinematic chain. Second, Hand4Whole discards the body feature when predicting 3D finger rotations. Our Hand4Whole is trained in an end-to-end manner and produces much better 3D hand results than previous whole-body 3D human mesh estimation methods. The codes are available here at https://github.com/mks0601/Hand4Whole_RELEASE.

Hongsuk Choi, Gyeongsik Moon, Ju Yong Chang et al.

Despite the recent success of single image-based 3D human pose and shape estimation methods, recovering temporally consistent and smooth 3D human motion from a video is still challenging. Several video-based methods have been proposed; however, they fail to resolve the single image-based methods' temporal inconsistency issue due to a strong dependency on a static feature of the current frame. In this regard, we present a temporally consistent mesh recovery system (TCMR). It effectively focuses on the past and future frames' temporal information without being dominated by the current static feature. Our TCMR significantly outperforms previous video-based methods in temporal consistency with better per-frame 3D pose and shape accuracy. We also release the codes. For the demo video, see https://youtu.be/WB3nTnSQDII. For the codes, see https://github.com/hongsukchoi/TCMR_RELEASE.

Hongsuk Choi, Gyeongsik Moon, Kyoung Mu Lee

Most of the recent deep learning-based 3D human pose and mesh estimation methods regress the pose and shape parameters of human mesh models, such as SMPL and MANO, from an input image. The first weakness of these methods is an appearance domain gap problem, due to different image appearance between train data from controlled environments, such as a laboratory, and test data from in-the-wild environments. The second weakness is that the estimation of the pose parameters is quite challenging owing to the representation issues of 3D rotations. To overcome the above weaknesses, we propose Pose2Mesh, a novel graph convolutional neural network (GraphCNN)-based system that estimates the 3D coordinates of human mesh vertices directly from the 2D human pose. The 2D human pose as input provides essential human body articulation information, while having a relatively homogeneous geometric property between the two domains. Also, the proposed system avoids the representation issues, while fully exploiting the mesh topology using a GraphCNN in a coarse-to-fine manner. We show that our Pose2Mesh outperforms the previous 3D human pose and mesh estimation methods on various benchmark datasets. For the codes, see https://github.com/hongsukchoi/Pose2Mesh_RELEASE.

Gyeongsik Moon, Kyoung Mu Lee

Most of the previous image-based 3D human pose and mesh estimation methods estimate parameters of the human mesh model from an input image. However, directly regressing the parameters from the input image is a highly non-linear mapping because it breaks the spatial relationship between pixels in the input image. In addition, it cannot model the prediction uncertainty, which can make training harder. To resolve the above issues, we propose I2L-MeshNet, an image-to-lixel (line+pixel) prediction network. The proposed I2L-MeshNet predicts the per-lixel likelihood on 1D heatmaps for each mesh vertex coordinate instead of directly regressing the parameters. Our lixel-based 1D heatmap preserves the spatial relationship in the input image and models the prediction uncertainty. We demonstrate the benefit of the image-to-lixel prediction and show that the proposed I2L-MeshNet outperforms previous methods. The code is publicly available https://github.com/mks0601/I2L-MeshNet_RELEASE.

Gyeongsik Moon, Heeseung Kwon, Kyoung Mu Lee et al.

Most current action recognition methods heavily rely on appearance information by taking an RGB sequence of entire image regions as input. While being effective in exploiting contextual information around humans, e.g., human appearance and scene category, they are easily fooled by out-of-context action videos where the contexts do not exactly match with target actions. In contrast, pose-based methods, which take a sequence of human skeletons only as input, suffer from inaccurate pose estimation or ambiguity of human pose per se. Integrating these two approaches has turned out to be non-trivial; training a model with both appearance and pose ends up with a strong bias towards appearance and does not generalize well to unseen videos. To address this problem, we propose to learn pose-driven feature integration that dynamically combines appearance and pose streams by observing pose features on the fly. The main idea is to let the pose stream decide how much and which appearance information is used in integration based on whether the given pose information is reliable or not. We show that the proposed IntegralAction achieves highly robust performance across in-context and out-of-context action video datasets. The codes are available in https://github.com/mks0601/IntegralAction_RELEASE.

Gyeongsik Moon, Ju Yong Chang, Kyoung Mu Lee

Although significant improvement has been achieved recently in 3D human pose estimation, most of the previous methods only treat a single-person case. In this work, we firstly propose a fully learning-based, camera distance-aware top-down approach for 3D multi-person pose estimation from a single RGB image. The pipeline of the proposed system consists of human detection, absolute 3D human root localization, and root-relative 3D single-person pose estimation modules. Our system achieves comparable results with the state-of-the-art 3D single-person pose estimation models without any groundtruth information and significantly outperforms previous 3D multi-person pose estimation methods on publicly available datasets. The code is available in https://github.com/mks0601/3DMPPE_ROOTNET_RELEASE , https://github.com/mks0601/3DMPPE_POSENET_RELEASE.

Gyeongsik Moon, Ju Yong Chang, Kyoung Mu Lee

Multi-person pose estimation from a 2D image is an essential technique for human behavior understanding. In this paper, we propose a human pose refinement network that estimates a refined pose from a tuple of an input image and input pose. The pose refinement was performed mainly through an end-to-end trainable multi-stage architecture in previous methods. However, they are highly dependent on pose estimation models and require careful model design. By contrast, we propose a model-agnostic pose refinement method. According to a recent study, state-of-the-art 2D human pose estimation methods have similar error distributions. We use this error statistics as prior information to generate synthetic poses and use the synthesized poses to train our model. In the testing stage, pose estimation results of any other methods can be input to the proposed method. Moreover, the proposed model does not require code or knowledge about other methods, which allows it to be easily used in the post-processing step. We show that the proposed approach achieves better performance than the conventional multi-stage refinement models and consistently improves the performance of various state-of-the-art pose estimation methods on the commonly used benchmark. The code is available in this https URL\footnote{\url{https://github.com/mks0601/PoseFix_RELEASE}}.

Gyeongsik Moon, Ju Yong Chang, Kyoung Mu Lee

Most of the existing deep learning-based methods for 3D hand and human pose estimation from a single depth map are based on a common framework that takes a 2D depth map and directly regresses the 3D coordinates of keypoints, such as hand or human body joints, via 2D convolutional neural networks (CNNs). The first weakness of this approach is the presence of perspective distortion in the 2D depth map. While the depth map is intrinsically 3D data, many previous methods treat depth maps as 2D images that can distort the shape of the actual object through projection from 3D to 2D space. This compels the network to perform perspective distortion-invariant estimation. The second weakness of the conventional approach is that directly regressing 3D coordinates from a 2D image is a highly non-linear mapping, which causes difficulty in the learning procedure. To overcome these weaknesses, we firstly cast the 3D hand and human pose estimation problem from a single depth map into a voxel-to-voxel prediction that uses a 3D voxelized grid and estimates the per-voxel likelihood for each keypoint. We design our model as a 3D CNN that provides accurate estimates while running in real-time. Our system outperforms previous methods in almost all publicly available 3D hand and human pose estimation datasets and placed first in the HANDS 2017 frame-based 3D hand pose estimation challenge. The code is available in https://github.com/mks0601/V2V-PoseNet_RELEASE.

Jonathan Samuel Lumentut, Kyoung Mu Lee

The field of 3D human-body reconstruction (abbreviated as 3DHR) that utilizes parametric pose and shape representations has witnessed significant advancements in recent years. However, the application of 3DHR techniques to handle real-world, diverse scenes, known as in-the-wild data, still faces limitations. The primary challenge arises as curating accurate 3D human pose ground truth (GT) for in-the-wild scenes is still difficult to obtain due to various factors. Recent test-time refinement approaches on 3DHR leverage initial 2D off-the-shelf human keypoints information to support the lack of 3D supervision on in-the-wild data. However, we observed that additional 2D supervision alone could cause the overfitting issue on common 3DHR backbones, making the 3DHR test-time refinement task seem intractable. We answer this challenge by proposing a strategy that complements 3DHR test-time refinement work under a collaborative approach. Specifically, we initially apply a pre-adaptation approach that works by collaborating various 3DHR models in a single framework to directly improve their initial outputs. This approach is then further combined with the test-time adaptation work under specific settings that minimize the overfitting issue to further boost the 3DHR performance. The whole framework is termed as 3DHR-Co, and on the experiment sides, we showed that the proposed work can significantly enhance the scores of common classic 3DHR backbones up to -34 mm pose error suppression, putting them among the top list on the in-the-wild benchmark data. Such achievement shows that our approach helps unveil the true potential of the common classic 3DHR backbones. Based on these findings, we further investigate various settings on the proposed framework to better elaborate the capability of our collaborative approach in the 3DHR task.

Yoshua Bengio, Sören Mindermann, Daniel Privitera et al. · eth-zurich, mit

The first International AI Safety Report comprehensively synthesizes the current evidence on the capabilities, risks, and safety of advanced AI systems. The report was mandated by the nations attending the AI Safety Summit in Bletchley, UK. Thirty nations, the UN, the OECD, and the EU each nominated a representative to the report's Expert Advisory Panel. A total of 100 AI experts contributed, representing diverse perspectives and disciplines. Led by the report's Chair, these independent experts collectively had full discretion over the report's content.

Jeongtaek Oh, Jaeyoung Chung, Dongwoo Lee et al.

Although significant progress has been made in reconstructing sharp 3D scenes from motion-blurred images, a transition to real-world applications remains challenging. The primary obstacle stems from the severe blur which leads to inaccuracies in the acquisition of initial camera poses through Structure-from-Motion, a critical aspect often overlooked by previous approaches. To address this challenge, we propose DeblurGS, a method to optimize sharp 3D Gaussian Splatting from motion-blurred images, even with the noisy camera pose initialization. We restore a fine-grained sharp scene by leveraging the remarkable reconstruction capability of 3D Gaussian Splatting. Our approach estimates the 6-Degree-of-Freedom camera motion for each blurry observation and synthesizes corresponding blurry renderings for the optimization process. Furthermore, we propose Gaussian Densification Annealing strategy to prevent the generation of inaccurate Gaussians at erroneous locations during the early training stages when camera motion is still imprecise. Comprehensive experiments demonstrate that our DeblurGS achieves state-of-the-art performance in deblurring and novel view synthesis for real-world and synthetic benchmark datasets, as well as field-captured blurry smartphone videos.

Mohsen Yavartanoo, Sangmin Hong, Reyhaneh Neshatavar et al.

The generation of industrial Computer-Aided Design (CAD) models from user requests and specifications is crucial to enhancing efficiency in modern manufacturing. Traditional methods of CAD generation rely heavily on manual inputs and struggle with complex or non-standard designs, making them less suited for dynamic industrial needs. To overcome these challenges, we introduce Text2CAD, a novel framework that employs stable diffusion models tailored to automate the generation process and efficiently bridge the gap between user specifications in text and functional CAD models. This approach directly translates the user's textural descriptions into detailed isometric images, which are then precisely converted into orthographic views, e.g., top, front, and side, providing sufficient information to reconstruct 3D CAD models. This process not only streamlines the creation of CAD models from textual descriptions but also ensures that the resulting models uphold physical and dimensional consistency essential for practical engineering applications. Our experimental results show that Text2CAD effectively generates technical drawings that are accurately translated into high-quality 3D CAD models, showing substantial potential to revolutionize CAD automation in response to user demands.

Xianghui Xie, Xi Wang, Nikos Athanasiou et al.

Modeling the interaction between humans and objects has been an emerging research direction in recent years. Capturing human-object interaction is however a very challenging task due to heavy occlusion and complex dynamics, which requires understanding not only 3D human pose, and object pose but also the interaction between them. Reconstruction of 3D humans and objects has been two separate research fields in computer vision for a long time. We hence proposed the first RHOBIN challenge: reconstruction of human-object interactions in conjunction with the RHOBIN workshop. It was aimed at bringing the research communities of human and object reconstruction as well as interaction modeling together to discuss techniques and exchange ideas. Our challenge consists of three tracks of 3D reconstruction from monocular RGB images with a focus on dealing with challenging interaction scenarios. Our challenge attracted more than 100 participants with more than 300 submissions, indicating the broad interest in the research communities. This paper describes the settings of our challenge and discusses the winning methods of each track in more detail. We observe that the human reconstruction task is becoming mature even under heavy occlusion settings while object pose estimation and joint reconstruction remain challenging tasks. With the growing interest in interaction modeling, we hope this report can provide useful insights and foster future research in this direction. Our workshop website can be found at \href{https://rhobin-challenge.github.io/}{https://rhobin-challenge.github.io/}.

Mohsen Yavartanoo, Sangmin Hong, Reyhaneh Neshatavar et al.

CNC manufacturing is a process that employs computer numerical control (CNC) machines to govern the movements of various industrial tools and machinery, encompassing equipment ranging from grinders and lathes to mills and CNC routers. However, the reliance on manual CNC programming has become a bottleneck, and the requirement for expert knowledge can result in significant costs. Therefore, we introduce a pioneering approach named CNC-Net, representing the use of deep neural networks (DNNs) to simulate CNC machines and grasp intricate operations when supplied with raw materials. CNC-Net constitutes a self-supervised framework that exclusively takes an input 3D model and subsequently generates the essential operation parameters required by the CNC machine to construct the object. Our method has the potential to transformative automation in manufacturing by offering a cost-effective alternative to the high costs of manual CNC programming while maintaining exceptional precision in 3D object production. Our experiments underscore the effectiveness of our CNC-Net in constructing the desired 3D objects through the utilization of CNC operations. Notably, it excels in preserving finer local details, exhibiting a marked enhancement in precision compared to the state-of-the-art 3D CAD reconstruction approaches.

Dongwoo Lee, Joonkyu Park, Kyoung Mu Lee

To train a deblurring network, an appropriate dataset with paired blurry and sharp images is essential. Existing datasets collect blurry images either synthetically by aggregating consecutive sharp frames or using sophisticated camera systems to capture real blur. However, these methods offer limited diversity in blur types (blur trajectories) or require extensive human effort to reconstruct large-scale datasets, failing to fully reflect real-world blur scenarios. To address this, we propose GS-Blur, a dataset of synthesized realistic blurry images created using a novel approach. To this end, we first reconstruct 3D scenes from multi-view images using 3D Gaussian Splatting (3DGS), then render blurry images by moving the camera view along the randomly generated motion trajectories. By adopting various camera trajectories in reconstructing our GS-Blur, our dataset contains realistic and diverse types of blur, offering a large-scale dataset that generalizes well to real-world blur. Using GS-Blur with various deblurring methods, we demonstrate its ability to generalize effectively compared to previous synthetic or real blur datasets, showing significant improvements in deblurring performance.

Jaerin Lee, JoonKyu Park, Sungyong Baik et al.

Image restoration models are typically trained with a pixel-wise distance loss defined over the RGB color representation space, which is well known to be a source of blurry and unrealistic textures in the restored images. The reason, we believe, is that the three-channel RGB space is insufficient for supervising the restoration models. To this end, we augment the representation to hold structural information of local neighborhoods at each pixel while keeping the color information and pixel-grainedness unharmed. The result is a new representation space, dubbed augmented RGB ($a$RGB) space. Substituting the underlying representation space for the per-pixel losses facilitates the training of image restoration models, thereby improving the performance without affecting the evaluation phase. Notably, when combined with auxiliary objectives such as adversarial or perceptual losses, our $a$RGB space consistently improves overall metrics by reconstructing both color and local structures, overcoming the conventional perception-distortion trade-off.

Suyoung Lee, Jaeyoung Chung, Kihoon Kim et al.

Feed-forward 3D Gaussian splatting (3DGS) models have gained significant popularity due to their ability to generate scenes immediately without needing per-scene optimization. Although omnidirectional images are becoming more popular since they reduce the computation required for image stitching to composite a holistic scene, existing feed-forward models are only designed for perspective images. The unique optical properties of omnidirectional images make it difficult for feature encoders to correctly understand the context of the image and make the Gaussian non-uniform in space, which hinders the image quality synthesized from novel views. We propose OmniSplat, a training-free fast feed-forward 3DGS generation framework for omnidirectional images. We adopt a Yin-Yang grid and decompose images based on it to reduce the domain gap between omnidirectional and perspective images. The Yin-Yang grid can use the existing CNN structure as it is, but its quasi-uniform characteristic allows the decomposed image to be similar to a perspective image, so it can exploit the strong prior knowledge of the learned feed-forward network. OmniSplat demonstrates higher reconstruction accuracy than existing feed-forward networks trained on perspective images. Our project page is available on: https://robot0321.github.io/omnisplat/index.html.

Peng Xu, Shengwu Xiong, Jiajun Zhang et al.

This paper reviews the MARS2 2025 Challenge on Multimodal Reasoning. We aim to bring together different approaches in multimodal machine learning and LLMs via a large benchmark. We hope it better allows researchers to follow the state-of-the-art in this very dynamic area. Meanwhile, a growing number of testbeds have boosted the evolution of general-purpose large language models. Thus, this year's MARS2 focuses on real-world and specialized scenarios to broaden the multimodal reasoning applications of MLLMs. Our organizing team released two tailored datasets Lens and AdsQA as test sets, which support general reasoning in 12 daily scenarios and domain-specific reasoning in advertisement videos, respectively. We evaluated 40+ baselines that include both generalist MLLMs and task-specific models, and opened up three competition tracks, i.e., Visual Grounding in Real-world Scenarios (VG-RS), Visual Question Answering with Spatial Awareness (VQA-SA), and Visual Reasoning in Creative Advertisement Videos (VR-Ads). Finally, 76 teams from the renowned academic and industrial institutions have registered and 40+ valid submissions (out of 1200+) have been included in our ranking lists. Our datasets, code sets (40+ baselines and 15+ participants' methods), and rankings are publicly available on the MARS2 workshop website and our GitHub organization page https://github.com/mars2workshop/, where our updates and announcements of upcoming events will be continuously provided.

Hyeongjin Nam, Donghwan Kim, Gyeongsik Moon et al.

The misaligned human texture across different human parts is one of the main limitations of existing 3D human reconstruction methods. Each human part, such as a jacket or pants, should maintain a distinct texture without blending into others. The structural coherence of human parts serves as a crucial cue to infer human textures in the invisible regions of a single image. However, most existing 3D human reconstruction methods do not explicitly exploit such part segmentation priors, leading to misaligned textures in their reconstructions. In this regard, we present PARTE, which utilizes 3D human part information as a key guide to reconstruct 3D human textures. Our framework comprises two core components. First, to infer 3D human part information from a single image, we propose a 3D part segmentation module (PartSegmenter) that initially reconstructs a textureless human surface and predicts human part labels based on the textureless surface. Second, to incorporate part information into texture reconstruction, we introduce a part-guided texturing module (PartTexturer), which acquires prior knowledge from a pre-trained image generation network on texture alignment of human parts. Extensive experiments demonstrate that our framework achieves state-of-the-art quality in 3D human reconstruction. The project page is available at https://hygenie1228.github.io/PARTE/.