Low-Rank Adaptation (LoRA) offers a parameter-efficient paradigm for tuning large models. While recent spectral initialization methods improve convergence and performance over the naive “Noise \& Zeros” scheme, their extra computational and storage overhead undermines efficiency. In this paper, we establish update magnitude as the fundamental driver of LoRA performance and propose LoRAM, a magnitude-driven “Basis \& Basis” initialization scheme that matches spectral methods without their inefficiencies. Our key contributions are threefold: (i) Magnitude of weight updates determines convergence. We prove low-rank structures intrinsically bound update magnitudes, unifying hyperparameter tuning in learning rate, scaling factor, and initialization as mechanisms to optimize magnitude regulation. (ii) Spectral initialization succeeds via magnitude amplification. We demystify that the presumed knowledge-driven benefit of spectral component essentially arises from the boost in the weight update magnitude. (iii) A novel and compact initialization strategy, LoRAM, scales deterministic orthogonal bases using pretrained weight magnitudes to simulate spectral gains. Extensive experiments show that LoRAM serves as a strong baseline, retaining the full efficiency of LoRA while matching or outperforming spectral initialization across benchmarks.

Reconstructing hand-held objects from monocular RGB images is an appealing yet challenging task. In this task, contacts between hands and objects provide important cues for recovering the 3D geometry of the hand-held objects. Though recent works have employed implicit functions to achieve impressive progress, they ignore formulating contacts in their frameworks, which results in producing less realistic object meshes. In this work, we explore how to model contacts in an explicit way to benefit the implicit reconstruction of hand-held objects. Our method consists of two components: explicit contact prediction and implicit shape reconstruction. In the first part, we propose a new subtask of directly estimating 3D hand-object contacts from a single image. The part-level and vertex-level graph-based transformers are cascaded and jointly learned in a coarse-to-fine manner for more accurate contact probabilities. In the second part, we introduce a novel method to diffuse estimated contact states from the hand mesh surface to nearby 3D space and leverage diffused contact probabilities to construct the implicit neural representation for the manipulated object. Benefiting from estimating the interaction patterns between the hand and the object, our method can reconstruct more realistic object meshes, especially for object parts that are in contact with hands. Extensive experiments on challenging benchmarks show that the proposed method outperforms the current state of the arts by a great margin. Our code is publicly available at https://junxinghu.github.io/projects/hoi.html.

Recently, video editing has made significant advances. Human character, as one of the core elements in video editing, has attracted great research attention. However, when editing characters with strong structural information, previous methods generally encounter blurring and distortion in the limbs. In this paper, we present EditHuman, a model to realize fine-grained text-driven human video editing tasks, which achieves continuous pose movements and high-quality limb expression. Considering complex body structures and continuity of motion, more precise designs are needed to obtain practical performance. Specifically, we propose a Cascaded UNet (CAU) to realize a coarse-to-fine denoising process and refined noise estimation. Meanwhile, we introduce two Heatmap-Centric Attention Modules called Key-Element Attention (KEA) and Key-Temporal Attention (KTA) to enhance the quality of human limb expression and inter-frame continuity. Moreover, we utilize the estimated heatmap to guide the noise prediction, which further refines the video quality. Extensive experiments show that EditHuman has achieved the SOTA performance.

3D human pose and shape estimation from a single RGB image is an appealing yet challenging task. Due to the graph-like nature of human parametric models, a growing number of graph neural network-based approaches have been proposed and achieved promising results. However, existing methods build graphs for different instances based on the same template SMPL mesh, neglecting the geometric perception of individual properties. In this work, we propose an end-to-end method named Personalized Graph Generation (PGG) to construct the geometry-aware graph from an intermediate predicted human mesh. Specifically, a convolutional module initially regresses a coarse SMPL mesh tailored for each sample. Guided by the 3D structure of this personalized mesh, PGG extracts the local features from the 2D feature map. Then, these geometry-aware features are integrated with the specific coarse SMPL parameters as vertex features. Furthermore, a body-oriented adjacency matrix is adaptively generated according to the coarse mesh. It considers individual full-body relations between vertices, enhancing the perception of body geometry. Finally, a graph attentional module is utilized to predict the residuals to get the final results. Quantitative experiments across four benchmarks and qualitative comparisons on more datasets show that the proposed method outperforms state-of-the-art approaches for 3D human pose and shape estimation.

Since the outbreak of the COVID-19 pandemic, iris recognition has been used increasingly as contactless and unaffected by face masks. Although less user cooperation is an urgent demand for existing systems, corresponding manually annotated databases could hardly be obtained. This paper presents a large-scale database of near-infrared iris images named CASIA-Iris-Degradation Version 1.0 (DV1), which consists of 15 subsets of various degraded images, simulating less cooperative situations such as illumination, off-angle, occlusion, and nonideal eye state. A lot of open-source segmentation and recognition methods are compared comprehensively on the DV1 using multiple evaluations, and the best among them are exploited to conduct ablation studies on each subset. Experimental results show that even the best deep learning frameworks are not robust enough on the database, and further improvements are recommended for challenging factors such as half-open eyes, off-angle, and pupil dilation. Therefore, we publish the DV1 with manual annotations online to promote iris recognition. (http://www.cripacsir.cn/dataset/)

The paper presents a summary of the 2020 Sclera Segmentation Benchmarking Competition (SSBC), the 7th in the series of group benchmarking efforts centred around the problem of sclera segmentation. Different from previous editions, the goal of SSBC 2020 was to evaluate the performance of sclera-segmentation models on images captured with mobile devices. The competition was used as a platform to assess the sensitivity of existing models to i) differences in mobile devices used for image capture and ii) changes in the ambient acquisition conditions. 26 research groups registered for SSBC 2020, out of which 13 took part in the final round and submitted a total of 16 segmentation models for scoring. These included a wide variety of deep-learning solutions as well as one approach based on standard image processing techniques. Experiments were conducted with three recent datasets. Most of the segmentation models achieved relatively consistent performance across images captured with different mobile devices (with slight differences across devices), but struggled most with low-quality images captured in challenging ambient conditions, i.e., in an indoor environment and with poor lighting.

Recently, although advanced satellite can collect massive image data, the efficiency of information extraction is still lacking due to low-quality and redundancy of data, and limited transmission bandwidth worsens this situation. As the result, researchers start to focus on software-defined satellite. Through directly deploying image processing applications on a space-based computing platform, satellite's capabilities can be flexibly changed, expanded or enhanced. Under such a trend, this paper proposes a global motion estimation system which attempts to reduce data redundancy in satellite videos. Our work consists of two stages: first, adaptively feature matching and optical flow are combined to estimate global motion. Following this, we give the transform formula between homography matrices in different resolution images, thus algorithm can be faster executed at a smaller search space. The proposed system runs on the Android platform, which is easy to be programmed, ported and updated. It is validated on the newest software-defined satellite TianZhi-1, and shows outstanding results under real experimental environment.