High-Quality Textured 3D Shape Reconstruction with Cascaded Fully Convolutional Networks

Liu, Zheng-Ning; Cao, Yan‐Pei; Kuang, Zhengfei; Kobbelt, Leif; Hu, Shi‐Min

doi:10.1109/tvcg.2019.2937300

Cited by 19 publications

(16 citation statements)

References 80 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our experiments used sequences from the Human10 dataset [4] to test our algorithm. This dataset contains 10 long sequences of several human actors performing various actions, of which 9 are publicly usable.…”

Section: Datasetmentioning

confidence: 99%

“…To demonstrate the ability of our system to generalize on real world scenes, we also selected some sequences from the DeepDeform dataset [7] and sequence human7 from the Human10 dataset [4] to test our method. Results are shown in Fig.…”

Section: Generalizationmentioning

confidence: 99%

“…15(a), although our Local-Fig. 14 Reconstruction results of sequences from DeepDeform dataset [7] and Human10 dataset [4] (bottom-left two). Compared to a traditional method [37] (blue), our method (red) can complete objects other than the human body and real scenes including interaction of people and things like a bag or ball.…”

Section: Limitationsmentioning

confidence: 99%

“…Since the early success of KinectFusion [1], scanning with a commodity RGB-D camera and reconstructing the captured geometry in an online fashion have become commonplace. Subsequent work has either improved system scalability to support larger scenes and finer details by introducing new persistent data structures [2][3][4], or focused on enhancing reconstruction quality through accurate frame-tomodel registration [5][6][7].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

HDR-Net-Fusion: Real-time 3D dynamic scene reconstruction with a hierarchical deep reinforcement network

et al. 2021

Self Cite

View full text Add to dashboard Cite

Reconstructing dynamic scenes with commodity depth cameras has many applications in computer graphics, computer vision, and robotics. However, due to the presence of noise and erroneous observations from data capturing devices and the inherently ill-posed nature of non-rigid registration with insufficient information, traditional approaches often produce low-quality geometry with holes, bumps, and misalignments. We propose a novel 3D dynamic reconstruction system, named HDR-Net-Fusion, which learns to simultaneously reconstruct and refine the geometry on the fly with a sparse embedded deformation graph of surfels, using a hierarchical deep reinforcement (HDR) network. The latter comprises two parts: a global HDR-Net which rapidly detects local regions with large geometric errors, and a local HDR-Net serving as a local patch refinement operator to promptly complete and enhance such regions. Training the global HDR-Net is formulated as a novel reinforcement learning problem to implicitly learn the region selection strategy with the goal of improving the overall reconstruction quality. The applicability and efficiency of our approach are demonstrated using a large-scale dynamic reconstruction dataset. Our method can reconstruct geometry with higher quality than traditional methods.

show abstract

Section: Datasetmentioning

confidence: 99%

Section: Generalizationmentioning

confidence: 99%

Section: Limitationsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

HDR-Net-Fusion: Real-time 3D dynamic scene reconstruction with a hierarchical deep reinforcement network

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…There are two types of human body shape acquisition techniques: (1) dynamic acquisitions techniques [PRMB15,CCS∗15,BBLR15,LFB17] that are focused on the natural movements of humans, such as motion capture and surface deformation, and (2) static acquisitions techniques [BBB∗10, RZY∗20] used for accurate human body shape reconstruction. In recent decades, many static active‐vision systems [TZL∗12, LCK∗21] and model‐based techniques [GWBB09, KBJM18] have been proposed for accurate human body shape reconstruction. It is generally believed that passive‐vision systems based on multi‐view stereo (MVS) are inferior to the above mainstream approaches, but that they have their advantages and tremendous potential.…”

Section: Introductionmentioning

confidence: 99%

A Robust Multi‐View System for High‐Fidelity Human Body Shape Reconstruction

Zhang

Wang

Liu

et al. 2021

Computer Graphics Forum

View full text Add to dashboard Cite

This paper proposes a passive multi‐view system for human body shape reconstruction, namely RHF‐Human, to overcome several challenges including accurate calibration and stereo matching in self‐occluded and low‐texture skin regions. The reconstruction process includes four steps: capture, multi‐view camera calibration, dense reconstruction, and meshing. The capture system, which consists of 90 digital single‐lens reflex cameras, is single‐shot to avoid nonrigid deformation of the human body. Two technical contributions are made: (1) a two‐step robust multi‐view calibration approach that improves calibration accuracy and saves calibration time for each new human body acquired and (2) an accurate PatchMatch multi‐view stereo method for dense reconstruction to perform correct matching in self‐occluded and low‐texture skin regions and to reduce the noise caused by body hair. Experiments on models of various genders, poses, and skin with different amounts of body hair show the robustness of the proposed system. A high‐fidelity human body shape dataset with 227 models is constructed, and the average accuracy is within 1.5 mm. The system provides a new scheme for the accurate reconstruction of nonrigid human models based on passive vision and has good potential in fashion design and health care.

show abstract

CIRCLE: Convolutional Implicit Reconstruction and Completion for Large-Scale Indoor Scene

Chen

Huang

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

High-Quality Textured 3D Shape Reconstruction with Cascaded Fully Convolutional Networks

Cited by 19 publications

References 80 publications

HDR-Net-Fusion: Real-time 3D dynamic scene reconstruction with a hierarchical deep reinforcement network

HDR-Net-Fusion: Real-time 3D dynamic scene reconstruction with a hierarchical deep reinforcement network

A Robust Multi‐View System for High‐Fidelity Human Body Shape Reconstruction

CIRCLE: Convolutional Implicit Reconstruction and Completion for Large-Scale Indoor Scene

Contact Info

Product

Resources

About