BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250522T212947Z
LOCATION:Mile High 1
DTSTART;TZID=America/Denver:20240731T140000
DTEND;TZID=America/Denver:20240731T153000
UID:siggraph_SIGGRAPH 2024_sess132@linklings.com
SUMMARY:Dynamic Radiance Fields
DESCRIPTION:4D-Rotor Gaussian Splatting: Towards Efficient Novel View Synt
 hesis for Dynamic Scenes\n\nWe present 4D-Rotor Gaussian Splatting that re
 presents dynamic scenes with anisotropic 4D XYZT Gaussians and rotor-based
  4D rotations for novel-view synthesis of dynamic scenes. The proposed met
 hod outperforms prior arts in rendering quality and achieves 277 FPS infer
 ence speed on an RTX 3090 GPU at...\n\n\nYuanxing Duan (Peking University)
 ; Fangyin Wei (Princeton University); Qiyu Dai (Peking University, State K
 ey Laboratory of General Artificial Intelligence); Yuhang He (Peking Unive
 rsity); Wenzheng Chen (NVIDIA, Peking University); and Baoquan Chen (Pekin
 g University, State Key Laboratory of General Artificial Intelligence)\n--
 -------------------\nST-4DGS: Spatial-Temporally Consistent 4D Gaussian Sp
 latting for Efficient Dynamic Scene Rendering\n\nOur ST-4DGS introduces an
  effective solution to prevent the compactness degeneration of 4D Gaussian
 s by using motion-aware shape regularization and spatial-temporal joint de
 nsity control, which is the key factor for better dynamic rendering qualit
 y in a more efficient manner.\n\n\nDeqi Li, Shi-Sheng Huang, Hua Huang, Zh
 iyuan Lu, and Xinran Duan (Beijing Normal University)\n-------------------
 --\nFactorized Motion Fields for Fast Sparse Input Dynamic View Synthesis\
 n\nThe performance of dynamic radiance fields reduces significantly with s
 parse input viewpoints. We design a fast and explicit motion-model using f
 actorized volumes and regularize with flow priors. Since cross-camera dens
 e-flow-priors are unreliable, we obtain reliable flow priors as a combinat
 ion of ...\n\n\nNagabhushan Somraj, Kapil Choudhary, Sai Harsha Mupparaju,
  and Rajiv Soundararajan (Indian Institute of Science)\n------------------
 ---\nDynamic Radiance Fields - Interactive Discussion\n\nAfter the summary
  presentations, attendees will participate in an interactive discussion. D
 istributed around the room will be a series of poster boards for authors t
 o gather around with the audience. Authors are invited to bring any materi
 al related to their paper that could instigate further conver...\n\n------
 ---------------\nModeling Ambient Scene Dynamics for Free-view Synthesis\n
 \nWe introduce an innovative method for view synthesis of dynamic scenes f
 rom one monocular video, enhancing immersion by overcoming previous limita
 tions of 3D Gaussian Splatting. By exploiting ambient motion periodicity a
 nd regularization, our approach reconstructs detailed natural scenes with 
 motion...\n\n\nMeng-Li Shih (University of Washington); Jia-Bin Huang (Uni
 versity of Maryland, College Park; Meta); and Changil Kim, Rajvi Shah, Joh
 annes Kopf, and Chen Gao (Meta)\n---------------------\nGaussianPrediction
 : Dynamic 3D Gaussian Prediction for Motion Extrapolation and Free View Sy
 nthesis\n\nWe present a novel framework, GaussianPrediction, for forecasti
 ng future scenarios in dynamic scenes. GaussianPrediction employs a 3D Gau
 ssian canonical space with deformation modeling and lifecycle property to 
 represent changes effectively. Additionally, a novel concentric motion dis
 tillation techn...\n\n\nBoming Zhao and Yuan Li (State Key Laboratory of C
 AD & CG, Zhejiang University); Ziyu Sun (Jilin University); Lin Zeng (Stat
 e Key Laboratory of CAD & CG, Zhejiang University); Yujun Shen (Ant Group)
 ; Rui Ma (Jilin University); Yinda Zhang (Google); and Hujun Bao and Zhaop
 eng Cui (State Key Laboratory of CAD & CG, Zhejiang University)\n---------
 ------------\nControllable Neural Style Transfer for Dynamic Meshes\n\nA n
 ovel mesh neural style transfer technique is presented. We improve upon th
 e previous stylization works through implicit re-parametrizations of meshe
 s, controllable style orientations, better temporal coherency treatment, a
 nd volume conservation. These improvements enable high-quality mesh styliz
 a...\n\n\nGuilherme Gomes Haetinger, Jingwei Tang, and Raphael Ortiz (Disn
 ey Research Studios); Paul Kanyuk (Pixar Animation Studios); and Vinicius 
 Azevedo (Disney Research Studios)\n\nInterest Area: Research & Education\n
 \nRegistration Category: Full Conference, Full Conference Supporter, Virtu
 al Access, Exhibitor Full Conference, Wednesday\n\nSession Chair: Min H. K
 im (Korea Advanced Institute of Science and Technology (KAIST))
END:VEVENT
END:VCALENDAR