BEGIN:VCALENDAR
PRODID:-//AddEvent Inc//AddEvent.com v1.7//EN
VERSION:2.0
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:STANDARD
DTSTART:20261101T010000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20260308T030000
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
DESCRIPTION:Volumetric videos offer immersive 4D experiences\, but remain difficult to reconstruct\, store\, and stream at scale. Existing Gaussian Splatting based methods achieve high-quality reconstruction but break down on long sequences\, temporal inconsistency\, and fail under large motions and disocclusions. Moreover\, their outputs are typically incompatible with conventional video coding pipelines\, preventing practical applications.\nRai et al. introduce PackUV\, a novel 4D Gaussian representation that maps all Gaussian attributes into a sequence of structured\, multi-scale UV atlas\, enabling compact\, image-native storage. To fit this representation from multi-view videos\, they propose PackUV-GS\, a temporally consistent fitting method that directly optimizes Gaussian parameters in the UV domain. An optical flow-guided Gaussian labeling and video keyframing module identifies dynamic Gaussians\, stabilizes static regions\, and preserves temporal coherence even under large motions and disocclusions. The resulting UV atlas format is the first unified volumetric video representation fully compatible with standard video codecs (e.g.\, FFV1) without losing quality\, enabling efficient streaming within existing multimedia infrastructure.\nTo evaluate long-duration volumetric capture\, they present PackUV-2B\, the largest multi-view video dataset to date\, featuring more than 50-90 synchronized cameras\, substantial motion\, and frequent disocclusions across 100+ sequences and over 2B (billion) frames. Extensive experiments demonstrate that the method surpasses existing baselines in rendering fidelity while scaling to sequences up to 30 minutes with consistent quality.\n\nAashish Rai is a Ph.D. student in Computer Science at Brown University\, advised by Srinath Sridhar. His research focuses on efficient methods for 3D and 4D novel view synthesis\, reconstruction\, and generative world modeling. He has also worked at Meta Reality Labs\, developing methods that leverage 2D foundation models for 3D asset synthesis. Previously\, he was a Research Assistant at Carnegie Mellon University’s Robotics Institute\, working with Fernando De la Torre on realistic 3D face generation using 2D models.\n\n------\n\nPowered by addevent.com \nShare your next event with us!\n
X-ALT-DESC;FMTTYPE=text/html:Volumetric videos offer immersive 4D experiences, but remain difficult to reconstruct, store, and stream at scale. Existing Gaussian Splatting based methods achieve high-quality reconstruction but break down on long sequences, temporal inconsistency, and fail under large motions and disocclusions. Moreover, their outputs are typically incompatible with conventional video coding pipelines, preventing practical applications.<br />Rai et al. introduce PackUV, a novel 4D Gaussian representation that maps all Gaussian attributes into a sequence of structured, multi-scale UV atlas, enabling compact, image-native storage. To fit this representation from multi-view videos, they propose PackUV-GS, a temporally consistent fitting method that directly optimizes Gaussian parameters in the UV domain. An optical flow-guided Gaussian labeling and video keyframing module identifies dynamic Gaussians, stabilizes static regions, and preserves temporal coherence even under large motions and disocclusions. The resulting UV atlas format is the first unified volumetric video representation fully compatible with standard video codecs (e.g., FFV1) without losing quality, enabling efficient streaming within existing multimedia infrastructure.<br />To evaluate long-duration volumetric capture, they present PackUV-2B, the largest multi-view video dataset to date, featuring more than 50-90 synchronized cameras, substantial motion, and frequent disocclusions across 100+ sequences and over 2B (billion) frames. Extensive experiments demonstrate that the method surpasses existing baselines in rendering fidelity while scaling to sequences up to 30 minutes with consistent quality.<br><br>Aashish Rai is a Ph.D. student in Computer Science at Brown University, advised by Srinath Sridhar. His research focuses on efficient methods for 3D and 4D novel view synthesis, reconstruction, and generative world modeling. He has also worked at Meta Reality Labs, developing methods that leverage 2D foundation models for 3D asset synthesis. Previously, he was a Research Assistant at Carnegie Mellon University’s Robotics Institute, working with Fernando De la Torre on realistic 3D face generation using 2D models.<br /><br />------<br /><br />Powered by addevent.com <br>Share your next event with us!<br>
UID:1775361356addeventcom
SUMMARY:Aashish Rai - Video-Native Representations for 4D Gaussian Scenes (CV)
DTSTART;TZID=America/Los_Angeles:20260414T080000
DTEND;TZID=America/Los_Angeles:20260414T090000
DTSTAMP:20260405T035556Z
TRANSP:OPAQUE
STATUS:CONFIRMED
SEQUENCE:0
LOCATION:https://meet.google.com/pqd-higu-fwa?hs=122&authuser=0
X-MICROSOFT-CDO-BUSYSTATUS:BUSY
BEGIN:VALARM
TRIGGER:-PT30M
ACTION:DISPLAY
DESCRIPTION:Reminder
END:VALARM
END:VEVENT
END:VCALENDAR