arXiv subjects

Hwann-Tzong Chen

Publications and source records attributed to Hwann-Tzong Chen.

At least 19 recordsLinked to original sources

arXiv2026

Event ActivityNet: A Large-Scale Simulated-Event Benchmark for Untrimmed Action Understanding

Long-horizon event-based action understanding remains underexplored because existing datasets largely comprise short, trimmed clips, while collecting native event streams with dense temporal annotations is costly. We introduce Event ActivityNet, a large-scale simulated-event benchmark derived from human-annotated, untrimmed ActivityNet videos. It comprises 3,263 videos, 200 action classes, and 106.94 hours, with matched 5-bin and 9-bin event-voxel representations, temporal action annotations, and timestamped captions. The benchmark supports annotated-segment action recognition, auxiliary event-language alignment, and causal online temporal action localization. We generate event voxels directly from non-interpolated source videos in decoded frame order, retain per-video rational nominal or average frame-rate metadata for approximate time mapping, and use action-center reconstruction LPIPS as a soft diagnostic of retained reconstructable content. We establish baselines for adaptive event framing, prompt-caption alignment, and event-only, RGB-only, and RGB-event localization. Under a progressive nested-scale training protocol, recognition Top-1 accuracy increases from 52.25 to 66.42, while online temporal localization average mAP improves from 21.7 to 29.0. Moreover, staged Event ActivityNet pretraining followed by native-event fine-tuning consistently outperforms target-only and joint-from-scratch training across multiple supervision budgets. Event ActivityNet provides a scalable benchmark for long-horizon event modeling, although native-camera evaluation remains essential for deployment-oriented conclusions.

cs.CV↗

arXiv2025

R2SM: Referring and Reasoning for Selective Masks

We introduce a new task, Referring and Reasoning for Selective Masks (R2SM), which extends text-guided segmentation by incorporating mask-type selection driven by user intent. This task challenges vision-language models to determine whether to generate a modal (visible) or amodal (complete) segmentation mask based solely on natural language prompts. To support the R2SM task, we present the R2SM dataset, constructed by augmenting annotations of COCOA-cls, D2SA, and MUVA. The R2SM dataset consists of both modal and amodal text queries, each paired with the corresponding ground-truth mask, enabling model finetuning and evaluation for the ability to segment images as per user intent. Specifically, the task requires the model to interpret whether a given prompt refers to only the visible part of an object or to its complete shape, including occluded regions, and then produce the appropriate segmentation. For example, if a prompt explicitly requests the whole shape of a partially hidden object, the model is expected to output an amodal mask that completes the occluded parts. In contrast, prompts without explicit mention of hidden regions should generate standard modal masks. The R2SM benchmark provides a challenging and insightful testbed for advancing research in multimodal reasoning and intent-aware segmentation.

cs.CV↗

arXiv2025

ErpGS: Equirectangular Image Rendering enhanced with 3D Gaussian Regularization

The use of multi-view images acquired by a 360-degree camera can reconstruct a 3D space with a wide area. There are 3D reconstruction methods from equirectangular images based on NeRF and 3DGS, as well as Novel View Synthesis (NVS) methods. On the other hand, it is necessary to overcome the large distortion caused by the projection model of a 360-degree camera when equirectangular images are used. In 3DGS-based methods, the large distortion of the 360-degree camera model generates extremely large 3D Gaussians, resulting in poor rendering accuracy. We propose ErpGS, which is Omnidirectional GS based on 3DGS to realize NVS addressing the problems. ErpGS introduce some rendering accuracy improvement techniques: geometric regularization, scale regularization, and distortion-aware weights and a mask to suppress the effects of obstacles in equirectangular images. Through experiments on public datasets, we demonstrate that ErpGS can render novel view images more accurately than conventional methods.

cs.CV↗

arXiv2025

Sparse2DGS: Sparse-View Surface Reconstruction using 2D Gaussian Splatting with Dense Point Cloud

Gaussian Splatting (GS) has gained attention as a fast and effective method for novel view synthesis. It has also been applied to 3D reconstruction using multi-view images and can achieve fast and accurate 3D reconstruction. However, GS assumes that the input contains a large number of multi-view images, and therefore, the reconstruction accuracy significantly decreases when only a limited number of input images are available. One of the main reasons is the insufficient number of 3D points in the sparse point cloud obtained through Structure from Motion (SfM), which results in a poor initialization for optimizing the Gaussian primitives. We propose a new 3D reconstruction method, called Sparse2DGS, to enhance 2DGS in reconstructing objects using only three images. Sparse2DGS employs DUSt3R, a fundamental model for stereo images, along with COLMAP MVS to generate highly accurate and dense 3D point clouds, which are then used to initialize 2D Gaussians. Through experiments on the DTU dataset, we show that Sparse2DGS can accurately reconstruct the 3D shapes of objects using just three images. The project page is available at https://gsisaoki.github.io/SPARSE2DGS/

cs.CV↗

arXiv2025

OB3D: A New Dataset for Benchmarking Omnidirectional 3D Reconstruction Using Blender

Recent advancements in radiance field rendering, exemplified by Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS), have significantly progressed 3D modeling and reconstruction. The use of multiple 360-degree omnidirectional images for these tasks is increasingly favored due to advantages in data acquisition and comprehensive scene capture. However, the inherent geometric distortions in common omnidirectional representations, such as equirectangular projection (particularly severe in polar regions and varying with latitude), pose substantial challenges to achieving high-fidelity 3D reconstructions. Current datasets, while valuable, often lack the specific focus, scene composition, and ground truth granularity required to systematically benchmark and drive progress in overcoming these omnidirectional-specific challenges. To address this critical gap, we introduce Omnidirectional Blender 3D (OB3D), a new synthetic dataset curated for advancing 3D reconstruction from multiple omnidirectional images. OB3D features diverse and complex 3D scenes generated from Blender 3D projects, with a deliberate emphasis on challenging scenarios. The dataset provides comprehensive ground truth, including omnidirectional RGB images, precise omnidirectional camera parameters, and pixel-aligned equirectangular maps for depth and normals, alongside evaluation metrics. By offering a controlled yet challenging environment, OB3Daims to facilitate the rigorous evaluation of existing methods and prompt the development of new techniques to enhance the accuracy and reliability of 3D reconstruction from omnidirectional images.

cs.CV↗

arXiv2025

EigenGS Representation: From Eigenspace to Gaussian Image Space

Principal Component Analysis (PCA), a classical dimensionality reduction technique, and 2D Gaussian representation, an adaptation of 3D Gaussian Splatting for image representation, offer distinct approaches to modeling visual data. We present EigenGS, a novel method that bridges these paradigms through an efficient transformation pipeline connecting eigenspace and image-space Gaussian representations. Our approach enables instant initialization of Gaussian parameters for new images without requiring per-image optimization from scratch, dramatically accelerating convergence. EigenGS introduces a frequency-aware learning mechanism that encourages Gaussians to adapt to different scales, effectively modeling varied spatial frequencies and preventing artifacts in high-resolution reconstruction. Extensive experiments demonstrate that EigenGS not only achieves superior reconstruction quality compared to direct 2D Gaussian fitting but also reduces necessary parameter count and training time. The results highlight EigenGS's effectiveness and generalization ability across images with varying resolutions and diverse categories, making Gaussian-based image representation both high-quality and viable for real-time applications.

cs.CV↗

arXiv2025

Segment Anything, Even Occluded

Amodal instance segmentation, which aims to detect and segment both visible and invisible parts of objects in images, plays a crucial role in various applications including autonomous driving, robotic manipulation, and scene understanding. While existing methods require training both front-end detectors and mask decoders jointly, this approach lacks flexibility and fails to leverage the strengths of pre-existing modal detectors. To address this limitation, we propose SAMEO, a novel framework that adapts the Segment Anything Model (SAM) as a versatile mask decoder capable of interfacing with various front-end detectors to enable mask prediction even for partially occluded objects. Acknowledging the constraints of limited amodal segmentation datasets, we introduce Amodal-LVIS, a large-scale synthetic dataset comprising 300K images derived from the modal LVIS and LVVIS datasets. This dataset significantly expands the training data available for amodal segmentation research. Our experimental results demonstrate that our approach, when trained on the newly extended dataset, including Amodal-LVIS, achieves remarkable zero-shot performance on both COCOA-cls and D2SA benchmarks, highlighting its potential for generalization to unseen scenarios.

cs.CV↗

arXiv2023

DiffusionAtlas: High-Fidelity Consistent Diffusion Video Editing

We present a diffusion-based video editing framework, namely DiffusionAtlas, which can achieve both frame consistency and high fidelity in editing video object appearance. Despite the success in image editing, diffusion models still encounter significant hindrances when it comes to video editing due to the challenge of maintaining spatiotemporal consistency in the object's appearance across frames. On the other hand, atlas-based techniques allow propagating edits on the layered representations consistently back to frames. However, they often struggle to create editing effects that adhere correctly to the user-provided textual or visual conditions due to the limitation of editing the texture atlas on a fixed UV mapping field. Our method leverages a visual-textual diffusion model to edit objects directly on the diffusion atlases, ensuring coherent object identity across frames. We design a loss term with atlas-based constraints and build a pretrained text-driven diffusion model as pixel-wise guidance for refining shape distortions and correcting texture deviations. Qualitative and quantitative experiments show that our method outperforms state-of-the-art methods in achieving consistent high-fidelity video-object editing.

cs.CV↗

arXiv2023

Seg2Reg: Differentiable 2D Segmentation to 1D Regression Rendering for 360 Room Layout Reconstruction

State-of-the-art single-view 360-degree room layout reconstruction methods formulate the problem as a high-level 1D (per-column) regression task. On the other hand, traditional low-level 2D layout segmentation is simpler to learn and can represent occluded regions, but it requires complex post-processing for the targeting layout polygon and sacrifices accuracy. We present Seg2Reg to render 1D layout depth regression from the 2D segmentation map in a differentiable and occlusion-aware way, marrying the merits of both sides. Specifically, our model predicts floor-plan density for the input equirectangular 360-degree image. Formulating the 2D layout representation as a density field enables us to employ `flattened' volume rendering to form 1D layout depth regression. In addition, we propose a novel 3D warping augmentation on layout to improve generalization. Finally, we re-implement recent room layout reconstruction methods into our codebase for benchmarking and explore modern backbones and training techniques to serve as the strong baseline. Our model significantly outperforms previous arts. The code will be made available upon publication.

cs.CV↗

arXiv2023

Hashing Neural Video Decomposition with Multiplicative Residuals in Space-Time

We present a video decomposition method that facilitates layer-based editing of videos with spatiotemporally varying lighting and motion effects. Our neural model decomposes an input video into multiple layered representations, each comprising a 2D texture map, a mask for the original video, and a multiplicative residual characterizing the spatiotemporal variations in lighting conditions. A single edit on the texture maps can be propagated to the corresponding locations in the entire video frames while preserving other contents' consistencies. Our method efficiently learns the layer-based neural representations of a 1080p video in 25s per frame via coordinate hashing and allows real-time rendering of the edited result at 71 fps on a single GPU. Qualitatively, we run our method on various videos to show its effectiveness in generating high-quality editing effects. Quantitatively, we propose to adopt feature-tracking evaluation metrics for objectively assessing the consistency of video editing. Project page: https://lightbulb12294.github.io/hashing-nvd/

cs.CV↗

arXiv2022

Multiview Regenerative Morphing with Dual Flows

This paper aims to address a new task of image morphing under a multiview setting, which takes two sets of multiview images as the input and generates intermediate renderings that not only exhibit smooth transitions between the two input sets but also ensure visual consistency across different views at any transition state. To achieve this goal, we propose a novel approach called Multiview Regenerative Morphing that formulates the morphing process as an optimization to solve for rigid transformation and optimal-transport interpolation. Given the multiview input images of the source and target scenes, we first learn a volumetric representation that models the geometry and appearance for each scene to enable the rendering of novel views. Then, the morphing between the two scenes is obtained by solving optimal transport between the two volumetric representations in Wasserstein metrics. Our approach does not rely on user-specified correspondences or 2D/3D input meshes, and we do not assume any predefined categories of the source and target scenes. The proposed view-consistent interpolation scheme directly works on multiview images to yield a novel and visually plausible effect of multiview free-form morphing.

cs.CV↗

arXiv2022

Improved Direct Voxel Grid Optimization for Radiance Fields Reconstruction

In this technical report, we improve the DVGO framework (called DVGOv2), which is based on Pytorch and uses the simplest dense grid representation. First, we re-implement part of the Pytorch operations with cuda, achieving 2-3x speedup. The cuda extension is automatically compiled just in time. Second, we extend DVGO to support Forward-facing and Unbounded Inward-facing capturing. Third, we improve the space time complexity of the distortion loss proposed by mip-NeRF 360 from O(N^2) to O(N). The distortion loss improves our quality and training speed. Our efficient implementation could allow more future works to benefit from the loss.

cs.GR↗

arXiv2022

Mask2Hand: Learning to Predict the 3D Hand Pose and Shape from Shadow

We present a self-trainable method, Mask2Hand, which learns to solve the challenging task of predicting 3D hand pose and shape from a 2D binary mask of hand silhouette/shadow without additional manually-annotated data. Given the intrinsic camera parameters and the parametric hand model in the camera space, we adopt the differentiable rendering technique to project 3D estimations onto the 2D binary silhouette space. By applying a tailored combination of losses between the rendered silhouette and the input binary mask, we are able to integrate the self-guidance mechanism into our end-to-end optimization process for constraining global mesh registration and hand pose estimation. The experiments show that our method, which takes a single binary mask as the input, can achieve comparable prediction accuracy on both unaligned and aligned settings as state-of-the-art methods that require RGB or depth inputs. Our code is available at https://github.com/lijenchang/Mask2Hand.

cs.CV↗

arXiv2022

Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction

We present a super-fast convergence approach to reconstructing the per-scene radiance field from a set of images that capture the scene with known poses. This task, which is often applied to novel view synthesis, is recently revolutionized by Neural Radiance Field (NeRF) for its state-of-the-art quality and flexibility. However, NeRF and its variants require a lengthy training time ranging from hours to days for a single scene. In contrast, our approach achieves NeRF-comparable quality and converges rapidly from scratch in less than 15 minutes with a single GPU. We adopt a representation consisting of a density voxel grid for scene geometry and a feature voxel grid with a shallow network for complex view-dependent appearance. Modeling with explicit and discretized volume representations is not new, but we propose two simple yet non-trivial techniques that contribute to fast convergence speed and high-quality output. First, we introduce the post-activation interpolation on voxel density, which is capable of producing sharp surfaces in lower grid resolution. Second, direct voxel density optimization is prone to suboptimal geometry solutions, so we robustify the optimization process by imposing several priors. Finally, evaluation on five inward-facing benchmarks shows that our method matches, if not surpasses, NeRF's quality, yet it only takes about 15 minutes to train from scratch for a new scene.

cs.CV↗

arXiv2022

Self-supervised 360$^{\circ}$ Room Layout Estimation

We present the first self-supervised method to train panoramic room layout estimation models without any labeled data. Unlike per-pixel dense depth that provides abundant correspondence constraints, layout representation is sparse and topological, hindering the use of self-supervised reprojection consistency on images. To address this issue, we propose Differentiable Layout View Rendering, which can warp a source image to the target camera pose given the estimated layout from the target image. As each rendered pixel is differentiable with respect to the estimated layout, we can now train the layout estimation model by minimizing reprojection loss. Besides, we introduce regularization losses to encourage Manhattan alignment, ceiling-floor alignment, cycle consistency, and layout stretch consistency, which further improve our predictions. Finally, we present the first self-supervised results on ZilloIndoor and MatterportLayout datasets. Our approach also shows promising solutions in data-scarce scenarios and active learning, which would have an immediate value in the real estate virtual tour software. Code is available at https://github.com/joshua049/Stereo-360-Layout.

cs.CV↗

arXiv2021

Pose Adaptive Dual Mixup for Few-Shot Single-View 3D Reconstruction

We present a pose adaptive few-shot learning procedure and a two-stage data interpolation regularization, termed Pose Adaptive Dual Mixup (PADMix), for single-image 3D reconstruction. While augmentations via interpolating feature-label pairs are effective in classification tasks, they fall short in shape predictions potentially due to inconsistencies between interpolated products of two images and volumes when rendering viewpoints are unknown. PADMix targets this issue with two sets of mixup procedures performed sequentially. We first perform an input mixup which, combined with a pose adaptive learning procedure, is helpful in learning 2D feature extraction and pose adaptive latent encoding. The stagewise training allows us to build upon the pose invariant representations to perform a follow-up latent mixup under one-to-one correspondences between features and ground-truth volumes. PADMix significantly outperforms previous literature on few-shot settings over the ShapeNet dataset and sets new benchmarks on the more challenging real-world Pix3D dataset.

cs.CV↗

arXiv2021

HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal Features

We present HoHoNet, a versatile and efficient framework for holistic understanding of an indoor 360-degree panorama using a Latent Horizontal Feature (LHFeat). The compact LHFeat flattens the features along the vertical direction and has shown success in modeling per-column modality for room layout reconstruction. HoHoNet advances in two important aspects. First, the deep architecture is redesigned to run faster with improved accuracy. Second, we propose a novel horizon-to-dense module, which relaxes the per-column output shape constraint, allowing per-pixel dense prediction from LHFeat. HoHoNet is fast: It runs at 52 FPS and 110 FPS with ResNet-50 and ResNet-34 backbones respectively, for modeling dense modalities from a high-resolution $512 \times 1024$ panorama. HoHoNet is also accurate. On the tasks of layout estimation and semantic segmentation, HoHoNet achieves results on par with current state-of-the-art. On dense depth estimation, HoHoNet outperforms all the prior arts by a large margin.

cs.CV↗

arXiv2021

Indoor Panorama Planar 3D Reconstruction via Divide and Conquer

Indoor panorama typically consists of human-made structures parallel or perpendicular to gravity. We leverage this phenomenon to approximate the scene in a 360-degree image with (H)orizontal-planes and (V)ertical-planes. To this end, we propose an effective divide-and-conquer strategy that divides pixels based on their plane orientation estimation; then, the succeeding instance segmentation module conquers the task of planes clustering more easily in each plane orientation group. Besides, parameters of V-planes depend on camera yaw rotation, but translation-invariant CNNs are less aware of the yaw change. We thus propose a yaw-invariant V-planar reparameterization for CNNs to learn. We create a benchmark for indoor panorama planar reconstruction by extending existing 360 depth datasets with ground truth H\&V-planes (referred to as PanoH&V dataset) and adopt state-of-the-art planar reconstruction methods to predict H\&V-planes as our baselines. Our method outperforms the baselines by a large margin on the proposed dataset.

cs.CV↗